{ "title": "2026-09-30 AI Daily | GPT-6.1 Sol one-fifth price anchors agent costs, ChatGPT identity portable, Manus 2.0 agent gets wallet", "url": "https://miaok.ong/en/ai-daily/ai-daily-2026-09-30/", "date": "2026-09-30T07:00:00+08:00", "lastmod": "2026-09-30T07:00:00+08:00", "type": "ai-daily", "kind": "page", "language": "en", "description": "OpenAI DevDay announced GPT-6.1 Sol, completing coding and professional work intelligence at one-fifth the price of Astra, and with Sign in with ChatGPT, allows subscription identities to flow across 16 tools. Manus 2.0 configures individual agents with independent email, phone, and wallet, transforming agents from tools into autonomous executors. Stratechery believes Meta\u0026rsquo;s opportunity lies in consumer agents, rather than enterprise platforms.", "keywords": null, "tags": [], "categories": [], "author": "Mark (Miao) Kong", "image": "https://miaok.ong/images/avatar.jpg", "content": "\u003ch1 id=\"2026-09-30-ai-daily--gpt-61-sol-anchors-agent-costs-at-one-fifth-the-price-chatgpt-identity-becomes-portable-manus-20-agents-get-wallets\"\u003e\n 2026-09-30 AI Daily | GPT-6.1 Sol Anchors Agent Costs at One-Fifth the Price, ChatGPT Identity Becomes Portable, Manus 2.0 Agents Get Wallets\n \u003ca class=\"heading-link\" href=\"#2026-09-30-ai-daily--gpt-61-sol-anchors-agent-costs-at-one-fifth-the-price-chatgpt-identity-becomes-portable-manus-20-agents-get-wallets\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h1\u003e\n\u003cblockquote\u003e\n\u003cp\u003eAt OpenAI DevDay, the company announced GPT-6.1 Sol, which enhances coding and professional work intelligence at one-fifth the price of Astra. \u0026ldquo;Sign in with ChatGPT\u0026rdquo; allows subscription identities to be used across 16 different tools. Manus 2.0 equips personal agents with independent email addresses, phone numbers, and wallets, transforming them from mere tools into autonomous entities. Stratechery argues that Meta\u0026rsquo;s opportunity lies in consumer agents, not enterprise platforms.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003ch2 id=\"-in-depth-guide-to-this-issues-watch-list\"\u003e\n šŸ“– In-Depth Guide to This Issue\u0026rsquo;s Watch List\n \u003ca class=\"heading-link\" href=\"#-in-depth-guide-to-this-issues-watch-list\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h2\u003e\n\u003cp\u003eThe most significant update to follow today is the combined announcement from OpenAI DevDay 2026 regarding GPT-6.1 Sol: Sol approaches the intelligence level of Astra for coding, computer use, and professional tasks at just one-fifth the price, effectively setting a new cost anchor for agent applications. Founders and engineering teams should carefully read the implementation details of the API, Codex, and security terms. Another noteworthy commentary relates to Meta, where the author bluntly states that Meta\u0026rsquo;s opportunity is in consumer agents, not enterprise platforms. This presents a strategic contrast to the OpenAI ecosystem, making it a valuable read for those interested in agent distribution. On the academic front, there are several papers on RAG and knowledge engineering worth reading: one jointly evaluates the interaction of parsers, chunking, and embeddings, while another uses trajectory variance to detect RAG conflicts in diffusion models. ChestPheNoT and OMP-MoE address the needs of medical text analysis and on-device deployment from the perspectives of auditable small models and expert pruning, respectively.\u003c/p\u003e\n\u003ch2 id=\"-ai-hotspots-on-x\"\u003e\n šŸŒ AI Hotspots on X\n \u003ca class=\"heading-link\" href=\"#-ai-hotspots-on-x\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h2\u003e\n\u003ch3 id=\"topic-1-openai-launches-gpt-61-sol-and-ai-collaboration-tools-at-devday-2026\"\u003e\n Topic 1: OpenAI Launches GPT-6.1 Sol and AI Collaboration Tools at DevDay 2026\n \u003ca class=\"heading-link\" href=\"#topic-1-openai-launches-gpt-61-sol-and-ai-collaboration-tools-at-devday-2026\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003eCategory: AI Ā· News\u003c/li\u003e\n\u003cli\u003eOverview: Trending Time:, Related Posts: 5000\u003c/li\u003e\n\u003cli\u003eWhat happened: At DevDay 2026, OpenAI announced GPT-6.1 Sol and several AI collaboration tools, pushing the transition from chatbots to AI colleagues.\u003c/li\u003e\n\u003cli\u003eWhy it\u0026rsquo;s important: The new model lowers the barrier to entry for high-performance AI with intelligence approaching Astra\u0026rsquo;s at a lower price and higher speed. It also enhances agent execution, cloud development, and team collaboration, potentially accelerating AI adoption in production environments.\u003c/li\u003e\n\u003cli\u003eDiscussion summary: Discussions on X focus on GPT-6.1 Sol\u0026rsquo;s cost-effectiveness and speed improvements, agent features like Dots, and the workflow changes brought by Codex Cloud and the Agents API. Points of disagreement mainly concern the significant availability differences of features across subscription tiers and whether the shift from conversational tools to agent systems will genuinely change daily work.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"topic-2-manus-launches-manus-20-with-independent-ai-agents-in-cue-app\"\u003e\n Topic 2: Manus Launches Manus 2.0 with Independent AI Agents in Cue App\n \u003ca class=\"heading-link\" href=\"#topic-2-manus-launches-manus-20-with-independent-ai-agents-in-cue-app\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003eCategory: AI Ā· News\u003c/li\u003e\n\u003cli\u003eOverview: Trending Time: 1 day ago, Related Posts: 8800\u003c/li\u003e\n\u003cli\u003eWhat happened: Manus released Manus 2.0 and the standalone app Cue, allowing users to create personal AI agents with their own email, phone number, wallet, and computing environment.\u003c/li\u003e\n\u003cli\u003eWhy it\u0026rsquo;s important: This indicates a shift for AI agents from passive tools to autonomous entities with identities and resources, which could drive competition in the personal AI assistant and agent economy.\u003c/li\u003e\n\u003cli\u003eDiscussion summary: Key topics on X include the autonomy and security boundaries of AI agents, whether personal agents will replace traditional app gateways, and the prospects for Manus\u0026rsquo;s independent development amidst US-China tech competition.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"topic-3-chatgpt-plus-and-pro-now-work-across-16-partner-apps\"\u003e\n Topic 3: ChatGPT Plus and Pro Now Work Across 16 Partner Apps\n \u003ca class=\"heading-link\" href=\"#topic-3-chatgpt-plus-and-pro-now-work-across-16-partner-apps\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003eCategory: AI Ā· News\u003c/li\u003e\n\u003cli\u003eOverview: Trending Time: 5 hours ago, Related Posts: 2500\u003c/li\u003e\n\u003cli\u003eWhat happened: At DevDay, OpenAI announced \u0026ldquo;Sign in with ChatGPT,\u0026rdquo; allowing ChatGPT Plus and Pro subscriptions to be used across 16 partner applications, including Devin, Notion, and Vercel.\u003c/li\u003e\n\u003cli\u003eWhy it\u0026rsquo;s important: This marks the beginning of portability for ChatGPT\u0026rsquo;s subscription identity, showing its evolution from a standalone chatbot to a cross-tool AI work platform and ecosystem gateway. This could change how AI applications are distributed and accessed by users.\u003c/li\u003e\n\u003cli\u003eDiscussion summary: Discussions on X center on OpenAI\u0026rsquo;s ecosystem ambitions, including announcements for plugins, agents, Codex, and workspaces. Disagreements focus on whether the $500 Pro pricing is justified, if the platform is creating lock-in for users and developers, and whether this represents a key turning point for ChatGPT\u0026rsquo;s evolution from a conversational tool to an \u0026ldquo;AI work operating system.\u0026rdquo;\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"topic-4-meta-launches-enterprise-ai-platform-with-mongodb-ceo\"\u003e\n Topic 4: Meta Launches Enterprise AI Platform with MongoDB CEO\n \u003ca class=\"heading-link\" href=\"#topic-4-meta-launches-enterprise-ai-platform-with-mongodb-ceo\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003eCategory: AI Ā· News\u003c/li\u003e\n\u003cli\u003eOverview: Trending Time: 1 day ago, Related Posts: 26000\u003c/li\u003e\n\u003cli\u003eWhat happened: Meta announced the launch of its enterprise AI platform and has hired MongoDB CEO Chirantan Desai to oversee the delivery of Muse agents and a full suite of AI tools to businesses and developers.\u003c/li\u003e\n\u003cli\u003eWhy it\u0026rsquo;s important: This marks Meta\u0026rsquo;s official commercialization of its AI stack and its entry into the enterprise AI market to compete with Microsoft, OpenAI, Anthropic, and others for enterprise customers, potentially altering the competitive landscape of enterprise AI.\u003c/li\u003e\n\u003cli\u003eDiscussion Summary: Key topics include whether Meta can leverage the experience of former MongoDB executives to penetrate the enterprise market, the future prospects of the Muse Enterprise Edition, and the significant drop in MongoDB\u0026rsquo;s stock price after its CEO was poached. Opinions are divided on whether Meta can effectively challenge the established enterprise AI vendors.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch4 id=\"summary-of-todays-ai-public-opinion-on-x\"\u003e\n Summary of Today\u0026rsquo;s AI Public Opinion on X\n \u003ca class=\"heading-link\" href=\"#summary-of-todays-ai-public-opinion-on-x\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h4\u003e\n\u003cp\u003eThe main theme in today\u0026rsquo;s discourse is the accelerating shift of AI from chatbots to \u0026ldquo;agent-based work platforms\u0026rdquo; equipped with identity, resources, and cross-application collaboration. OpenAI is promoting the flow of low-cost, high-performance models and subscription identities across tools with GPT-6.1 Sol and \u0026ldquo;Sign in with ChatGPT.\u0026rdquo; Manus 2.0 provides personal agents with independent email, wallets, and computing environments, while Meta has also officially entered the enterprise agent market. The consensus is that lowering the barrier to high-performance models and integrating AI agents into actual production and personal workflows has become a shared goal. The main points of disagreement focus on the reasonableness of subscription tiers and the $500 Pro pricing, whether platforms are locking in users and developers through ecosystem integration, whether autonomous agents will replace traditional application entry points, and whether latecomers like Meta can truly challenge the existing enterprise AI landscape. The potential risk is that a consensus on agent autonomy and security boundaries has not yet been formed. Further opening up identity, payment, and computing resources could magnify the risks of misuse, abuse, and dependency on centralized platforms.\u003c/p\u003e\n\u003ch2 id=\"-influencer-insights\"\u003e\n šŸ’” Influencer Insights\n \u003ca class=\"heading-link\" href=\"#-influencer-insights\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003eInfluencer insights are unavailable today. We recommend reading the in-depth content from the Watch List.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003ch2 id=\"-appendix-todays-watch-list-source-update-list\"\u003e\n šŸ“š Appendix: Today\u0026rsquo;s Watch List Source Update List\n \u003ca class=\"heading-link\" href=\"#-appendix-todays-watch-list-source-update-list\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003eTime window: Last 3 days; 22 sources covered; 34 updates in total\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003ch3 id=\"stratechery-by-ben-thompson-a_full\"\u003e\n Stratechery by Ben Thompson (A_full)\n \u003ca class=\"heading-link\" href=\"#stratechery-by-ben-thompson-a_full\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003e\u003ca href=\"https://stratechery.com/2026/one-more-note-on-agents-meta-connect-meta-enterprise-platform/\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eOne More Note on Agents, Meta Connect, Meta Enterprise Platform\u003c/a\u003e\u003c/strong\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 18:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - Meta has the chance to own the consumer agentic space; going for enterprise is a big mistake.\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003e$15\u003c/strong\u003e/month* or *\u003cstrong\u003e$150\u003c/strong\u003e/year.\u003c/li\u003e\n\u003cli\u003eSubstantive analysis of the dayā€™s news via three weekly emails or a podcast.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eStrategy Interviews\u003c/strong\u003e.\u003c/li\u003e\n\u003cli\u003eInterviews with leading public company CEOs, private company founders, and discussions with fellow analysts.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003eMeta has the chance to own the consumer agentic space; going for enterprise is a big mistake.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"openai-blog-a_full\"\u003e\n OpenAI Blog (A_full)\n \u003ca class=\"heading-link\" href=\"#openai-blog-a_full\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://openai.com/index/introducing-gpt-6-1-sol\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eIntroducing GPT-6.1 Sol\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 18:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - Meet GPT-6.1 Sol: near-Astra intelligence for coding, computer use, and professional work at one-fifth of Astraā€™s standard API input and output token prices.\n\u003cul\u003e\n\u003cli\u003eThis article from the OpenAI blog explains how the launch of GPT-6.1 Sol is shaping the broader artificial intelligence and infrastructure landscape.\u003c/li\u003e\n\u003cli\u003eIt also covers the practical implications for founders, operators, and investors following the launch of GPT-6.1 Sol.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003eMeet GPT-6.1 Sol: near-Astra intelligence for coding, computer use, and professional work at one-fifth of Astraā€™s standard API input and output token prices.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://openai.com/index/devday-2026-recap\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eDevDay 2026 Recap\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 18:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - Explore the 20+ announcements from OpenAI DevDay 2026, including GPT-6 Astra, ChatGPT, Codex, APIs, safety, and new tools for builders.\n\u003cul\u003e\n\u003cli\u003eThis article from the OpenAI blog explains how the DevDay 2026 Recap is shaping the broader artificial intelligence and infrastructure landscape.\u003c/li\u003e\n\u003cli\u003eIt also covers the practical implications for founders, operators, and investors following the DevDay 2026 recap.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eExplore more than 20 announcements from OpenAI DevDay 2026, including GPT-6 Astra, ChatGPT, Codex, APIs, security, and new tools for builders.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://openai.com/index/introducing-dots\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eIntroducing dots\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePosted: 2026-09-29 08:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - Dots by OpenAI is a proactive assistant that can work continuously on complex projects and everyday tasks.\n\u003cul\u003e\n\u003cli\u003eLearn how dots help you stay in control while work moves forward.\u003c/li\u003e\n\u003cli\u003eDots by OpenAI is a proactive assistant that can continue to work on complex projects and everyday tasks. Learn how dots help you stay in control while work moves forward.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003eDots by OpenAI are a proactive assistant that can keep working across complex projects and everyday tasks\u003c/li\u003e\n\u003cli\u003eLearn how dots help you stay in control while work moves forward.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"arxiv-csai-b_introsearch\"\u003e\n ArXiv cs.AI (B_intro+search)\n \u003ca class=\"heading-link\" href=\"#arxiv-csai-b_introsearch\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31763\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eSMARtCARE: Privacy-Preserving Agentic AI Systems for Bounded-Autonomy Clinical Decision Support\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePosted: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31763v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Long-context clinical AI systems can miss relevant patient history when prior admissions fall outside the active reasoning context.\u003c/li\u003e\n\u003cli\u003eIn ICU monitoring, this can cause early vital-sign drift to appear nonspecific even when it resembles a prior deterioration pattern.\u003c/li\u003e\n\u003cli\u003eSMARtCARE addresses this gap through a four-state clinical decision-support architecture: Stable, Meta-cognitive, Assisted, and Regulated (Revoked).\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31763v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Long-context clinical AI systems can miss relevant patient history when prior admissions fall outside the active reasoning context\u003c/li\u003e\n\u003cli\u003eIn ICU monitoring, this can cause early vital-sign drift to appear nonspecific even when it resembles a prior deterioration pattern\u003c/li\u003e\n\u003cli\u003eSMARtCARE addresses this gap through a four-state clinical decision-support architecture: Stable, Meta-cognitive, Assisted, and Regulated (Revoked)\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31784\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eWiteness Overlap: Directional Provenance Inside Open-Weight Model Families\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePosted: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31784v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Open-weight models are frequently released, fine-tuned, aligned, merged, and republished, making provenance audits ask not just whether checkpoints are related, but which came first.\u003c/li\u003e\n\u003cli\u003eMany existing model provenance methods are designed for audit settings where the foundation is known: given a victim or source model, they test if a suspect model is related to it.\u003c/li\u003e\n\u003cli\u003eAlthough these audits are designed as source-to-suspect tests, their underlying evidence is often symmetric, relying on representation similarity, weight similarity, behavioral fingerprints, or related statistics.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31784v1 Announce Type: new\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eAbstract: Open-weight models are often released, fine-tuned, aligned, merged, and re-released, making provenance audits ask not only whether checkpoints are relā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eMany existing model-provenance methods are designed for a base-known audit setting: given a victim or source model, they test whether a suspect model is relatedā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eAlthough these audits are framed as source-to-suspect tests, their underlying evidence is often symmetric, relying on representation similarity, weight similariā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31790\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eCP-Agent: A Harness-Engineered Agent for Crystal Plasticity Simulation Workflows\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31790v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Crystal plasticity (CP) simulations can predict the mechanical behavior of polycrystalline metals, but their routine use is hindered by manual operations such as configuring heterogeneous tools, orchestrating multi-step data pipelines, and calibrating constitutive parameters based on experiments.\u003c/li\u003e\n\u003cli\u003eThese bottlenecks hinder productivity in systematic parameter studies, sparking interest in automated workflows.\u003c/li\u003e\n\u003cli\u003eThis study introduces CP-Agent, an LLM-based harness-engineered agent that can autonomously execute a complete CP modeling workflow based on natural language tasks.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31790v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Crystal plasticity (CP) simulations predict the mechanical behavior of polycrystalline metals, yet their routine use is hindered by the manual effortā€¦\u003c/li\u003e\n\u003cli\u003eThese bottlenecks impede productivity in systematic parameter studies, motivating interest in automated workflows\u003c/li\u003e\n\u003cli\u003eThis study presents CP-Agent, a harness-engineered LLM-based agent that autonomously executes complete CP modeling workflows from natural-language tasks\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31792\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise Conflicts\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31792v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: While Vision-Language-Action (VLA) models perform strongly on manipulation tasks, their responses to invalid task premises remain underexplored.\u003c/li\u003e\n\u003cli\u003eExisting premise conflict evaluations typically focus on the final task outcome, but task failure itself cannot distinguish between behavioral disengagement and continued pursuit following an execution error.\u003c/li\u003e\n\u003cli\u003eWe term this latter pattern failure persistence.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31792v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: While Vision-Language-Action (VLA) models perform strongly on manipulation tasks, their responses to invalid task premises remain underexplored\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eExisting evaluations of premise conflicts often focus on terminal task outcomes, yet task failure alone cannot distinguish behavioral disengagement from continuā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eWe call the latter pattern Failed Persistence\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31793\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eWorking with AI: A Design Framework for Human-AI Collaboration\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time:2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract:- arXiv:2609.31793v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Artificial Intelligence (AI), particularly GenAI, is becoming an increasingly important part of modern work.\u003c/li\u003e\n\u003cli\u003eIn industrial settings, AI can support decision-making, automate routine activities, assist humans, and improve productivity.\u003c/li\u003e\n\u003cli\u003eHowever, the successful adoption of AI depends on more than just the technical capabilities.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN 要ē‚¹:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31793v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Artificial Intelligence (AI), particularly GenAI, is becoming an increasingly important part of modern work\u003c/li\u003e\n\u003cli\u003eIn industrial settings, AI can support decision-making, automate routine activities, assist humans, and improve productivity\u003c/li\u003e\n\u003cli\u003eHowever, successful AI adoption depends on more than what the technology can do\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31814\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eDriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time:2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract:- arXiv:2609.31814v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Evaluating VLM-based autonomous driving remains difficult because driving capability is composite; a capable system must ground traffic participants and hazards, integrate context across views and time, reason about future evolutions, and take appropriate actions under closed-loop interaction.\u003c/li\u003e\n\u003cli\u003eExisting benchmarks typically evaluate open-loop understanding or closed-loop driving, but provide limited structure to explain how these capabilities are organized, how they relate to each other, and how they inform model diagnosis and improvement.\u003c/li\u003e\n\u003cli\u003eWe propose \\textsc{DriveHierarchy}, a hierarchical benchmark that categorizes VLM-based autonomous driving into four ranks, covering perceptual grounding, contextual memory, psychological reasoning, and closed-loop execution.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN 要ē‚¹:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31814v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Evaluating VLM-based autonomous driving remains difficult because driving competence is composite, where a capable system must ground traffic participā€¦\u003c/li\u003e\n\u003cli\u003eExisting benchmarks usually assess either open-loop understanding or closed-loop driving but provide limited structure for explaining how these abilities are orā€¦\u003c/li\u003e\n\u003cli\u003eWe present \\textsc{DriveHierarchy}, a hierarchical benchmark that organizes VLM-based autonomous driving into four ranks, spanning perceptual grounding, contextā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31857\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eLLM Judge Validation Under Sparse Overlap: From Inference to Design\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31857v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Validating an LLM as a judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled.\u003c/li\u003e\n\u003cli\u003eWe prove that this \\emph{overlap sparsity} is the first-order determinant of wrong deployment decisions: at 5% pairwise overlap, wrong-decision rates reach 25%, and the probability of selecting the wrong best judgment among 10 candidates is 65%.\u003c/li\u003e\n\u003cli\u003eThe two actionable levers are overlap \\emph{quantity} and \\emph{allocation}.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31857v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled\u003c/li\u003e\n\u003cli\u003eWe prove that this \\emph{overlap sparsity} is the first-order determinant of wrong deployment decisions: at 5% pairwise overlap, wrong-decision rates reach 25\\ā€¦\u003c/li\u003e\n\u003cli\u003eThe two actionable levers are overlap \\emph{quantity} and \\emph{allocation}\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31868\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eMetro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31868v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Model-predictive control with Joint-Embedding Predictive Architectures (JEPAs) provides a strong zero-shot goal-reaching planner, but it is only effective within a short-term planning horizon.\u003c/li\u003e\n\u003cli\u003eHierarchical extensions attempt to bridge this gap by learning a macro planner to predict intermediate latent sub-goals to guide the micro planner.\u003c/li\u003e\n\u003cli\u003eIn this work, we demonstrate that unconstrained latent sub-goal prediction is fundamentally flawed.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31868v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Model-predictive control with Joint-Embedding Predictive Architectures (JEPAs) provides a strong zero-shot goal-reaching planner, but it is only effecā€¦\u003c/li\u003e\n\u003cli\u003eHierarchical extensions attempt to bridge this gap by learning a macro planner to predict intermediate latent sub-goals to guide the micro planner\u003c/li\u003e\n\u003cli\u003eIn this work, we demonstrate that unconstrained latent sub-goal prediction is fundamentally flawed\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31871\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eIndustryLLM: Failure-Driven LLM Training for Industrial Procurement\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31871v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Industrial procurement requires language models to bridge the gap between informal buyer terminology, sparse market attributes, and authoritative engineering standards under strict safety tolerances.\u003c/li\u003e\n\u003cli\u003eWe introduce IndustryLLM, an open-weight industrial language model trained from Qwen3.5-35B-A3B-Base (35B total parameters, ~3B activated per token, with the visual encoder frozen).\u003c/li\u003e\n\u003cli\u003eInstead of relying on general-purpose text scaling, we introduce a failure-driven adaptation method that covers both continued pre-training (CPT) and supervised fine-tuning (SFT).\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003earXiv:2609.31871v1 Announce Type: new\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eAbstract: Industrial procurement requires language models to bridge informal buyer jargon, sparse marketplace attributes, and authoritative engineering standardā€¦\u003c/li\u003e\n\u003cli\u003eWe present IndustryLLM, an open-weight industrial language model trained from Qwen3.5-35B-A3B-Base (35B total parameters with ~3B activated per token, with theā€¦\u003c/li\u003e\n\u003cli\u003eRather than relying on generic text scaling, we introduce a failure-driven adaptation recipe spanning continued pre-training (CPT) and supervised fine-tuning (Sā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31874\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eCOUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31874v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Existing agent memory frameworks mainly create memory through an agent\u0026rsquo;s interaction with the factual world, e.g., remembering feedback from actions taken to improve future task performance.\u003c/li\u003e\n\u003cli\u003eHowever, these frameworks seldom ask the \u0026ldquo;what if\u0026rdquo; question during memory construction: what if a different action had been taken, would the feedback have changed? How could such feedback become useful memory?\u003c/li\u003e\n\u003cli\u003eObtaining such feedback directly in an active environment can be expensive and can alter the state needed for comparison.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31874v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Existing agent memory frameworks mainly create memory through an agent\u0026rsquo;s interaction with the factual world, e.g., remembering feedback from actions tā€¦\u003c/li\u003e\n\u003cli\u003eHowever, these frameworks seldom ask the \u0026ldquo;what if\u0026rdquo; question during memory construction: what if a different action had been taken, would the feedback have changā€¦\u003c/li\u003e\n\u003cli\u003eObtaining such feedback directly in an active environment can be expensive and can alter the state needed for comparison\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"arxiv-cscl-b_introsearch\"\u003e\n ArXiv cs.CL (B_intro+search)\n \u003ca class=\"heading-link\" href=\"#arxiv-cscl-b_introsearch\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31629\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reports\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31629v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Extracting structured phenotypes from radiology reports supports cohort construction, quality audits, and clinical analysis, but real-world deployment requires local inference and auditable predictions, while expert annotations remain scarce.\u003c/li\u003e\n\u003cli\u003eTraditional labels provide structured findings and assertion statuses but without supporting evidence, and API-hosted large language models may be unsuitable when clinical text cannot leave the institutional infrastructure.\u003c/li\u003e\n\u003cli\u003eWe propose CHESTPHENOT, a compact 0.5-3B language model that jointly extracts finding labels, a ternary status (present/absent/uncertain), and verbatim supporting evidence spans.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31629v1 Announce Type: new\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eAbstract: Structured phenotype extraction from radiology reports supports cohort construction, quality auditing, and clinical analytics, but practical deploymenā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eConventional labelers provide structured findings and assertion states but no supporting evidence, while API-hosted large language models may be unsuitable whenā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eWe present CHESTPHENOT, a compact 0.5-3B language model that jointly extracts finding labels, three-class status (present/absent/uncertain), and verbatim supporā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31650\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eA literature-guided descriptor-based framework for filtering composition search spaces\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31650v1 Announcement Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Scientific literature contains latent knowledge about materials behavior, but much of this knowledge is expressed through words, contexts, and recurring associations, rather than through explicit design principles.\u003c/li\u003e\n\u003cli\u003eThis raises a central question: how can large-scale scientific corpora be used for practical problems in materials discovery?\u003c/li\u003e\n\u003cli\u003eHere, we present a literature-guided, descriptor-based filtering framework for reducing composition search spaces.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31650v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Scientific literature contains latent knowledge about materials behavior, but much of this knowledge is expressed through words, contexts, and recurriā€¦\u003c/li\u003e\n\u003cli\u003eThis raises a central question: how can large-scale scientific corpora be used for practical problems in materials discovery\u003c/li\u003e\n\u003cli\u003eHere, we present a literature-guided descriptor-based filtering framework for reducing composition search spaces\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31653\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eDistributional sentiment modeling and anomaly detection for consumer complaint assessment\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31653v1 Announcement Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Sentiment analysis is a common tool in finance and risk management for converting unstructured text into quantitative signals.\u003c/li\u003e\n\u003cli\u003eHowever, most applications reduce the output to discrete polarity labels or a single predictive feature, ignoring the distributional structure of sentiment intensity in consumer complaint narratives.\u003c/li\u003e\n\u003cli\u003eIn this paper, we treat negative sentiment in consumer complaints as a bounded continuous variable and study its full distribution rather than a single label.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31653v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Sentiment analysis is a common tool for converting unstructured text into quantitative signals in finance and risk management\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eYet most applications reduce the output to a discrete polarity label or a single predictive feature, overlooking the distributional structure of sentiment intenā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eIn this paper we treat negative sentiment in consumer complaints as a bounded continuous variable and study its full distribution rather than a single label\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31660\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eParser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documents\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31660v1 Announcement Type: New.\nAbstract: Retrieval-Augmented Generation (RAG) pipelines are typically assembled from independently-chosen components (document parsers, chunking strategies, and embedding models), but these choices are rarely evaluated jointly, and their combined evaluation often runs on a single document or corpus.\n\u003cul\u003e\n\u003cli\u003eWe propose a controlled factorial study involving 3 parsers, 3 chunking strategies, and 5 dense embedding models, along with a sparse BM25 baseline, evaluated against 800 question instances. Each instance has one or more required evidence strings, which are automatically validated against the source text and manually reviewed in a 10% random sample, covering four structurally distinct Indian central government regulatory documents.\u003c/li\u003e\n\u003cli\u003eWe fit a linear mixed-effects model with document-query-level random intercepts to the resulting 72,000-row result set, run Holm-corrected paired comparisons between matched dense and sparse configurations, and report cluster-bootstrapped confidence intervals for all 54 unique retriever configurations.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31660v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Retrieval-augmented generation (RAG) pipelines are typically assembled from independently-chosen components \u0026ndash; a document parser, a chunking strategy,ā€¦\u003c/li\u003e\n\u003cli\u003eWe present a controlled factorial study of 3 parsers, 3 chunking strategies, and 5 dense embedding models, together with a sparse BM25 baseline, evaluated againā€¦\u003c/li\u003e\n\u003cli\u003eWe fit linear mixed-effects models with document-query-level random intercepts to the resulting 72,000-row result set, run Holm-corrected paired comparisons betā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31663\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eLLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31663v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Building ontology-driven knowledge graphs from industrial texts remains challenging due to the domain-specificity of documents, the scarcity of annotation resources, and the complexity of ontology engineering workflows.\u003c/li\u003e\n\u003cli\u003eThis paper proposes and investigates the applicability of an ontology learning pipeline that combines compact, open-source Large Language Models (LLMs), reusable prompting strategies, and open knowledge bases to support the extraction, structuring, enrichment, and evaluation of knowledge from text corpora.\u003c/li\u003e\n\u003cli\u003eThe method was tested and evaluated on a corpus of French private power grid incident reports using locally deployable open-source LLMs with parameters ranging from 7B to 32B.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31663v1 Announce Type: new\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eAbstract: Ontology-driven knowledge graph construction from industrial text remains challenging due to the domain specificity of documents, the scarcity of annoā€¦\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eThis paper presents and investigates the applicability of an ontology learning pipeline that combines compact open-source Large Language Models (LLMs), reusableā€¦\u003c/li\u003e\n\u003cli\u003eThe approach is tested and evaluated on a private French corpus of power-grid incident reports, using locally deployable open-source LLMs ranging from 7B to 32Bā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31664\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eWhat Drives Dialectal Jailbreaks? An Ablation of Surface Form, Cultural Framing, and Strategy Banks\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublished: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31664v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Recent work suggests that obscure language registers can weaken large language model refusal behavior, especially when paired with black-box prompt optimization.\u003c/li\u003e\n\u003cli\u003eIt remains unclear whether failures stem from non-standard surface form, culturally grounded framing, or optimization over an expressive prompt-strategy space.\u003c/li\u003e\n\u003cli\u003eWe study Chinese registers by extending a classical-Chinese red-teaming framework to Shanghainese and Cantonese and running a 36-cell ablation across surface form, strategy bank variants, and two target models.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31664v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Recent work suggests that obscure language registers can weaken large language model refusal behavior, especially when paired with black-box prompt opā€¦\u003c/li\u003e\n\u003cli\u003eIt remains unclear whether failures stem from non-standard surface form, culturally grounded framing, or optimization over an expressive prompt-strategy space\u003c/li\u003e\n\u003cli\u003eWe study Chinese registers by extending a classical-Chinese red-teaming framework to Shanghainese and Cantonese and running a 36-cell ablation across surface foā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31666\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eAge-Adaptive Handwriting Reconstruction from an IMU-Based Digital Pen through Shared Representations and Domain-Specific Heads\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublished: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31666v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Digital pens are widely used to capture handwriting on digital devices, enabling precise trace recording and enhancing human-computer interaction.\u003c/li\u003e\n\u003cli\u003eHowever, most are bundled with tablets and lack cross-brand compatibility.\u003c/li\u003e\n\u003cli\u003eRecently, digital pens equipped with motion sensors have emerged, designed for use on any surface.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31666v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Digital pens are widely used to capture handwriting on digital devices, enabling precise trace recording and enhancing human-computer interaction\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eHowever, most are bundled with tablets and lack cross-brand compatibility\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eRecent digital pens equipped with kinematic sensors have emerged, designed for use on any surface\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31676\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eAn Evaluation of AI-Supported Evidence-Based Learning for Public Speaking Skill Development\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31676v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Public speaking is an essential skill in academic and professional contexts, but it often causes anxiety.\u003c/li\u003e\n\u003cli\u003eAlthough several AI-based speech coaching tools exist, they typically provide generic feedback and lack model speeches for learning.\u003c/li\u003e\n\u003cli\u003eThis study addresses these gaps by developing a system that incorporates speech context into evaluation criteria, enabling more tailored feedback.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31676v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Public speaking is an essential skill in academic and professional contexts, but it often causes anxiety\u003c/li\u003e\n\u003cli\u003eAlthough several AI-based speech coaching tools exist, they typically provide generic feedback and lack model speeches for learning\u003c/li\u003e\n\u003cli\u003eThis study addresses these gaps by developing a system that incorporates speech context into evaluation criteria, enabling more tailored feedback\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31684\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eThe Temporal Tug-of-War: Visualizing and Detecting RAG Conflicts in Diffusion Models via Trajectory Variance\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31684v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Retrieval-Augmented Generation (RAG) introduces a specific failure mode in discrete diffusion language models: when the retrieved context contradicts parametric knowledge, the iterative denoising process becomes a visible battleground between competing knowledge sources.\u003c/li\u003e\n\u003cli\u003eWe identify temporal semantic divergence as an observable for detecting these conflicts and introduce the Trajectory Variance Score (TVS), a simple and interpretable measure of divergence.\u003c/li\u003e\n\u003cli\u003eTVS computes the mean pairwise cosine distance of answer embeddings across independent stochastic denoising trajectories, capturing the temporal tug-of-war between parametric and contextual attractors.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31684v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Retrieval-Augmented Generation (RAG) introduces a specific failure mode in discrete diffusion language models: when retrieved context contradicts paraā€¦\u003c/li\u003e\n\u003cli\u003eWe identify temporal semantic divergence as an observable for detecting these conflicts and introduce the Trajectory Variance Score (TVS), a simple and interpreā€¦\u003c/li\u003e\n\u003cli\u003eTVS computes the mean pairwise cosine distance of answer embeddings across independent stochastic denoising trajectories, capturing the temporal tug of war betwā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31687\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eVerification of PETSc with CIVL using LLM-generated ACSL contracts and deterministic driver generation\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublished: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31687v1 Announcement Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Parallel numerical libraries (such as PETSc) are widely used in scientific and engineering applications, where erroneous results can have costly consequences.\u003c/li\u003e\n\u003cli\u003eDespite this, numerical libraries are rarely formally verified.\u003c/li\u003e\n\u003cli\u003eOne of the challenges is the need for an expert to hand-write specifications and manually apply a verification tool, often requiring the development of harnesses or drivers, all of which can introduce additional errors, leading to false positives or negatives during verification.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31687v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Parallel numerical libraries such as PETSc are widely used in science and engineering applications where wrong results can have costly consequences\u003c/li\u003e\n\u003cli\u003eDespite this, numerical libraries are rarely formally verified\u003c/li\u003e\n\u003cli\u003eOne of the challenges is the need for an expert to hand-write a specification and manually apply a verification tool, often requiring the development of a harneā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"arxiv-cslg-b_introsearch\"\u003e\n ArXiv cs.LG (B_intro+search)\n \u003ca class=\"heading-link\" href=\"#arxiv-cslg-b_introsearch\"\u003e\n \u003ci class=\"fa-solid fa-link\" aria-hidden=\"true\" title=\"Link to heading\"\u003e\u003c/i\u003e\n \u003cspan class=\"sr-only\"\u003eLink to heading\u003c/span\u003e\n \u003c/a\u003e\n\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31630\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eReplay in the Silent Degrees of Freedom: Continual Learning Without an Offline Phase\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublished: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31630v1 Announcement Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Replay-based continual learning almost always consolidates in a dedicated offline phase or by interleaving replayed samples with the input stream, whereas the brain also consolidates during waking periods through local sleepā€”brief, use-dependent shutdown periods of individual circuits.\u003c/li\u003e\n\u003cli\u003eWe ask whether a network trained by local, biologically constrained rules can consolidate with no offline phase at all.\u003c/li\u003e\n\u003cli\u003eAn isolation rule confines replay updates to hidden synapses invisible to the current input under k-winner-take-all dynamics, with optimizer state advanced only within the mask; a refractory rotation rule prevents just-fired units from participating in the next competition, broadening the scope of what can be consolidated; homeostatic pressure and a relative novelty gate determine when replay bursts and when rotation operates.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31630v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Replay-based continual learning almost always consolidates in a dedicated offline phase or by interleaving replayed samples with the input stream, wheā€¦\u003c/li\u003e\n\u003cli\u003eWe ask whether a network trained by local, biologically constrained rules can consolidate with no offline phase at all\u003c/li\u003e\n\u003cli\u003eAn isolation rule confines replay updates to hidden synapses invisible to the current input under k-winner-take-all dynamics, with optimiser state advanced onlyā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31631\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eOMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublished: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31631v1 Announcement Type: new.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eAbstract: Mixture-of-Experts (MoE) models can effectively scale large language models, but face critical deployment challenges due to massive memory requirements.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eExisting pruning methods either incur prohibitive search costs or neglect the dynamic interdependencies between experts.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eTo address these challenges, we propose OMP-MoE, a novel training-free compression framework for reducing expert redundancy in MoE-based LLMs.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eEN Key Points:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31631v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Mixture-of-Experts (MoE) models enable efficient scaling of large language models but face critical deployment challenges due to massive memory requirā€¦\u003c/li\u003e\n\u003cli\u003eExisting pruning methods either incur prohibitive search costs or neglect the dynamic interdependencies between experts\u003c/li\u003e\n\u003cli\u003eTo address these challenges, we present OMP-MoE, a novel training-free compression framework for reducing expert redundancy in MoE-based LLMs\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31632\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eEEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eRelease Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31632v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eElectroencephalography (EEG) analysis is evolving from short-segment classification toward long-horizon interpretation, which requires iterative evidence accumulation, multi-step reasoning, and the coordinated use of professional signal processing tools.\u003c/li\u003e\n\u003cli\u003eAlthough Large Language Models (LLMs) have recently shown promise as autonomous agents for EEG analysis, existing EEG agentic evaluations remain fragmented, covering limited tasks within a narrow timeframe, with inconsistent protocols, and without providing a comprehensive assessment of the agent\u0026rsquo;s reasoning, tool use, and workflow construction abilities.\u003c/li\u003e\n\u003cli\u003eTo address this gap, we propose \\textbf{EEGAgentBench}, a unified benchmark for systematically evaluating LLM agents on short- and long-horizon EEG analysis.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31632v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Electroencephalography (EEG) analysis is evolving from short-segment classification toward long-horizon interpretation that demands iterative evidenceā€¦\u003c/li\u003e\n\u003cli\u003eAlthough large language models (LLMs) have recently shown promise as autonomous agents for EEG analysis, existing EEG agentic evaluations remain fragmented, covā€¦\u003c/li\u003e\n\u003cli\u003eTo address this gap, we propose \\textbf{EEGAgentBench}, a unified benchmark for systematically evaluating LLM agents on short- and long-horizon EEG analysis\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31633\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eEnhancing generalization in endwall film cooling prediction: Incorporating the superposition principle into transformer-based neural operators\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eRelease Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31633v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eIn this study, a physics-enhanced neural operator framework is proposed to enhance the generalization prediction capability for turbine endwall cooling layouts with a variable number of film holes.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eSpecifically, inspired by the film cooling superposition principle, we propose a film cooling prediction model, namely the Superposition-based Deep Neural Operator (SDNO), which divides the endwall temperature field prediction into two stages.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eIn the first stage, the cooling layout of a turbine endwall is divided into several sub-parts with randomly assigned film holes, and a Transformer-based neural operator network (i.e., Calculate Net) is designed to predict the temperature field of each sub-part.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31633v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: In this study, a physics-enhanced neural operator framework is proposed to enhance the generalization prediction ability of the cooling layout of a tuā€¦\u003c/li\u003e\n\u003cli\u003eSpecifically, inspired by the film cooling superposition principle, we propose a film cooling prediction model, namely superposition-based deep neural operatorā€¦\u003c/li\u003e\n\u003cli\u003eIn the first stage, the cooling layout of a turbine endwall is divided into several sub-parts with randomly assigned film holes, and a Transformer-based neuralā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31634\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eSymmetry-quotient Flatness and Generalization\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eRelease Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31634v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: This paper develops a theorem-level pipeline in a symmetry-quotient setting: quotient linear stability implies quotient flatness, quotient flatness implies input smoothness, and input smoothness yields generalization under a local covering assumption.\u003c/li\u003e\n\u003cli\u003eFlatness is often associated with generalization, and Stochastic Gradient Descent (SGD) is frequently viewed as implicitly biased toward flat solutions.\u003c/li\u003e\n\u003cli\u003eHowever, standard flatness measures are typically defined in the raw parameter space and are therefore not invariant under function-preserving symmetries such as positive rescaling.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31634v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: This paper develops a theorem-level pipeline in symmetry-quotient settings: quotient linear stability implies quotient flatness, quotient flatness impā€¦\u003c/li\u003e\n\u003cli\u003eFlatness is often associated with generalization, and Stochastic Gradient Descent (SGD) is frequently viewed as implicitly biased toward flat solutions\u003c/li\u003e\n\u003cli\u003eHowever, standard flatness measures are typically defined in the raw parameter space and are therefore not invariant under function-preserving symmetries such aā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31635\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eWhat Next-Event Accuracy Cannot See: Closed-Loop Evaluation of Emergency Department Trajectory Simulators\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eRelease Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31635v1 Announce Type: new.\n\u003cul\u003e\n\u003cli\u003eAbstract: Clinical trajectory models are typically evaluated by their observational next-event accuracy.\u003c/li\u003e\n\u003cli\u003eSimulation is different: models must condition on their own generated events, allowing errors to compound.\u003c/li\u003e\n\u003cli\u003eWhile this issue is well-known in sequence modeling, it has not been systematically quantified for clinical trajectory simulators.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31635v1 Announce Type: new\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eAbstract: Clinical trajectory models are usually evaluated by next-event accuracy on observed histories\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eSimulation is different: models must condition on their own generated events, allowing errors to compound\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eAlthough this problem is well known in sequence modelling, it has not been systematically quantified for clinical trajectory simulators\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31636\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eGrounding Vision-Language Models in Driving Semantics: A Multi-Dataset Predicate Framework for Explainable Reasoning\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31636v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Vision-language models are increasingly used for driving scene understanding, but the semantic relationships expressed in their outputs are often difficult to validate against the underlying traffic conditions.\u003c/li\u003e\n\u003cli\u003eThis paper introduces a deterministic multi-dataset predicate framework that derives driving scene semantics from measurable geometric, kinematic, temporal, map, and traffic control evidence.\u003c/li\u003e\n\u003cli\u003eDataset-specific interfaces are used only to recover the required scene information, while predicate definitions remain unchanged across nuPlan and nuScene and are materialized in a universal predicate knowledge graph.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31636v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Vision-language models are increasingly used for driving-scene understanding, yet the semantic relations expressed in their outputs are often difficulā€¦\u003c/li\u003e\n\u003cli\u003eThis paper introduces a deterministic multi-dataset predicate framework that derives driving-scene semantics from measurable geometric, kinematic, temporal, mapā€¦\u003c/li\u003e\n\u003cli\u003eDataset-specific interfaces are used only to recover the required scene information, while predicate definitions remain unchanged across nuPlan and nuScenes andā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31637\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eFIDAL: Diversity-Aware Federated Active Learning Under Real-World Distribution Shifts\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePublication Time: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31637v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Federated learning enables collaborative model training across institutions without centralizing data, but high annotation costs, domain shifts, and class imbalances remain major obstacles, especially when irrelevant out-of-distribution (OOD) samples dilute the labeled data.\u003c/li\u003e\n\u003cli\u003eExisting active learning methods target uncertainty or diversity in in-distribution (ID) data and overlook unknown samples in a federated clinical environment.\u003c/li\u003e\n\u003cli\u003eWe propose FIDAL, an open-set federated active learning framework that combines calibrated global-local evidential uncertainty, support set diversity weighting, and adaptive OOD rejection.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Key Points:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31637v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Federated learning enables collaborative model training across institutions without centralizing data, yet high annotation costs, domain shifts, and cā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eExisting active learning methods target uncertainty or diversity within in-distribution (ID) data and overlook unknown samples in federated clinical settings\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eWe propose FIDAL, an open-set federated active learning framework that combines calibrated global-local evidential uncertainty, support-set diversity weighting,ā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31638\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eEnergy-aware frugal Bayesian optimization\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePosted on: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31638v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: The primary goal of modern design optimization frameworks is to provide the most accurate predictive models without balancing computational overhead.\u003c/li\u003e\n\u003cli\u003eThis remains a reason why large-scale architectural and multidisciplinary design optimization problems are difficult to solve, even with sample-efficient Bayesian optimizers.\u003c/li\u003e\n\u003cli\u003eIn this paper, a metric quantifying the computational energy footprint is introduced within a Bayesian optimization framework to guide the model\u0026rsquo;s parameter settings to achieve a balance between performance and a frugal configuration.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31638v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Modern design optimization frameworks aim first and foremost for models with the most accurate predictions without balancing computational overhead\u003c/li\u003e\n\u003cli\u003eIt remains a reason why scaled architecture and multidisciplinary design optimization problems are difficult to address, even with sample-efficient Bayesian optā€¦\u003c/li\u003e\n\u003cli\u003eIn this paper, a metric quantifying the computational energy footprint is introduced within a Bayesian optimization framework to guide the parameter setting ofā€¦\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://arxiv.org/abs/2609.31639\" class=\"external-link\" target=\"_blank\" rel=\"noopener\"\u003eWhen Does Domain Adaptation Help on Physical Vibration Sensors? A Held-Out-Bearing Study of Neural-Operator and Convolutional Models\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePosted on: 2026-09-29 12:00 Beijing Time\u003c/li\u003e\n\u003cli\u003eAbstract: - arXiv:2609.31639v1 Announcement Type: New.\n\u003cul\u003e\n\u003cli\u003eAbstract: Diagnosing rolling-element bearing faults through vibration is a canonical physical-sensing task and a widely used benchmark for domain adaptation under changing operating conditions.\u003c/li\u003e\n\u003cli\u003eAccuracies exceeding 99% are commonly reported, but the evaluations use the same physical bearing in both training and testing.\u003c/li\u003e\n\u003cli\u003eWe revisit the task under a held-out bearing protocol, assigning each bearing unit entirely to either the training or test set, and find that source-only transfer is far weaker than these numbers suggest: it reaches only 0.36 when shaft speed varies, while the target-supervised upper bound is 0.97.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003eEN Highlights:\n\u003cul\u003e\n\u003cli\u003earXiv:2609.31639v1 Announce Type: new\u003c/li\u003e\n\u003cli\u003eAbstract: Diagnosing rolling-element bearing faults from vibration is a canonical physical-sensing task and a widely used benchmark for domain adaptation underā€¦\u003c/li\u003e\n\u003cli\u003eAccuracies above 99 percent are commonly reported, but under evaluation splits that place the same physical bearing in both training and test\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eWe revisit the task under a held-out-bearing protocol, assigning every bearing unit entirely to either the training or the test set, and find that source-only tā€¦\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n", "wordCount": 6363, "readingTime": 30, "tableOfContents": "\u003cnav id=\"TableOfContents\"\u003e\n \u003cul\u003e\n \u003cli\u003e\u003ca href=\"#-in-depth-guide-to-this-issues-watch-list\"\u003ešŸ“– In-Depth Guide to This Issue\u0026rsquo;s Watch List\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#-ai-hotspots-on-x\"\u003ešŸŒ AI Hotspots on X\u003c/a\u003e\n \u003cul\u003e\n \u003cli\u003e\u003ca href=\"#topic-1-openai-launches-gpt-61-sol-and-ai-collaboration-tools-at-devday-2026\"\u003eTopic 1: OpenAI Launches GPT-6.1 Sol and AI Collaboration Tools at DevDay 2026\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#topic-2-manus-launches-manus-20-with-independent-ai-agents-in-cue-app\"\u003eTopic 2: Manus Launches Manus 2.0 with Independent AI Agents in Cue App\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#topic-3-chatgpt-plus-and-pro-now-work-across-16-partner-apps\"\u003eTopic 3: ChatGPT Plus and Pro Now Work Across 16 Partner Apps\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#topic-4-meta-launches-enterprise-ai-platform-with-mongodb-ceo\"\u003eTopic 4: Meta Launches Enterprise AI Platform with MongoDB CEO\u003c/a\u003e\u003c/li\u003e\n \u003c/ul\u003e\n \u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#-influencer-insights\"\u003ešŸ’” Influencer Insights\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#-appendix-todays-watch-list-source-update-list\"\u003ešŸ“š Appendix: Today\u0026rsquo;s Watch List Source Update List\u003c/a\u003e\n \u003cul\u003e\n \u003cli\u003e\u003ca href=\"#stratechery-by-ben-thompson-a_full\"\u003eStratechery by Ben Thompson (A_full)\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#openai-blog-a_full\"\u003eOpenAI Blog (A_full)\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#arxiv-csai-b_introsearch\"\u003eArXiv cs.AI (B_intro+search)\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#arxiv-cscl-b_introsearch\"\u003eArXiv cs.CL (B_intro+search)\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003e\u003ca href=\"#arxiv-cslg-b_introsearch\"\u003eArXiv cs.LG (B_intro+search)\u003c/a\u003e\u003c/li\u003e\n \u003c/ul\u003e\n \u003c/li\u003e\n \u003c/ul\u003e\n\u003c/nav\u003e", "isDraft": false }