web_fetch/005_arxiv_recent_ai-2

{
  "tool_name": "web_fetch",
  "tool_input": {
    "brief": "Get the 20 most recent cs.AI submissions",
    "max_age_seconds": 3600,
    "url": "https://arxiv.org/list/cs.AI/recent"
  },
  "dispatch_id": "toolu_01SoJtnjs57jbki7SrHJ1TKb",
  "parent_dispatch_id": "",
  "handle": "",
  "panel_kind": "web_fetch"
}

{
  "tool_name": "web_fetch",
  "dispatch_id": "toolu_01SoJtnjs57jbki7SrHJ1TKb",
  "status": "running",
  "result": null,
  "error": "",
  "elapsed": null,
  "fields": {
    "progress": {
      "message": "Get the 20 most recent cs.AI submissions",
      "metadata": {
        "browser_chain": false,
        "url": "https://arxiv.org/list/cs.AI/recent"
      }
    },
    "status": "running",
    "updatedAt": 1789168227804
  }
}

{
  "tool_name": "web_fetch",
  "dispatch_id": "toolu_01SoJtnjs57jbki7SrHJ1TKb",
  "status": "completed",
  "result": {
    "content": "Artificial Intelligence\n\n [Skip to main content](#content)\n\n [https://arxiv.org/IgnoreMe](https://arxiv.org/IgnoreMe) [![archive](/static/base/1.0.1/images/arxiv-logo-primary-light.svg)](https://arxiv.org/)\n\n[Search](https://arxiv.org/search) [Submit](https://arxiv.org/user/create) [Donate](https://info.arxiv.org/about/donate.html)  [Log in](https://arxiv.org/login)\n\n\n\n\n\n\n\n  Search arXiv\n\n Press Enter to search · [Advanced search](https://arxiv.org/search/advanced)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n# Artificial Intelligence\n\n\n\n## Authors and titles for recent submissions\n\n\n -  [Fri, 11 Sep 2026](/list/cs.AI/recent?skip=0&show=50)\n-  [Thu, 10 Sep 2026](/list/cs.AI/recent?skip=171&show=50)\n-  [Wed, 9 Sep 2026](/list/cs.AI/recent?skip=321&show=50)\n-  [Mon, 7 Sep 2026](/list/cs.AI/recent?skip=838&show=50)\n-  [Fri, 4 Sep 2026](/list/cs.AI/recent?skip=1043&show=50)\n\n\n\nSee today's [new](/list/cs.AI/new) changes\n\n\n\nTotal of 1208 entries : 1-50 [51-100](/list/cs.AI/recent?skip=50&show=50) [101-150](/list/cs.AI/recent?skip=100&show=50) [151-200](/list/cs.AI/recent?skip=150&show=50) ... [1201-1208](/list/cs.AI/recent?skip=1200&show=50)\n\n\n\nShowing up to 50 entries per page: [fewer](/list/cs.AI/recent?skip=0&show=25) | [more](/list/cs.AI/recent?skip=0&show=100) | [all](/list/cs.AI/recent?skip=0&show=2000)\n\n\n\n### Fri, 11 Sep 2026 (showing first 50 of 171 entries )\n\n  [1] [arXiv:2609.11916](/abs/2609.11916) [[pdf](/pdf/2609.11916), [html](https://arxiv.org/html/2609.11916v1), [other](/format/2609.11916)]\n\n\n\nTitle: Can Edge-Deployable Vision-Language Models Identify Species?\n\n\n\n[William Zhou](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Mayukha Siripuram](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiao Yan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ziqi Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yi Ding](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [2] [arXiv:2609.11911](/abs/2609.11911) [[pdf](/pdf/2609.11911), [html](https://arxiv.org/html/2609.11911v1), [other](/format/2609.11911)]\n\n\n\nTitle: Artificial Id: Drive and Persistent Alignment in Agentic AI\n\n\n\n[Yakov Pyotr Shkolnikov](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [3] [arXiv:2609.11900](/abs/2609.11900) [[pdf](/pdf/2609.11900), [html](https://arxiv.org/html/2609.11900v1), [other](/format/2609.11900)]\n\n\n\nTitle: MindTopo: Can Foundation Models Reason in Topological Space?\n\n\n\n[Yunfei Ge](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Anbang Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Qineng Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Johnalbert Garnica](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jianwen Lyu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zihan Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Reuben Tan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jianfeng Gao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ruohan Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yining Hong](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jiajun Wu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Manling Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: Preprint version\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)\n\n\n\n   [4] [arXiv:2609.11876](/abs/2609.11876) [[pdf](/pdf/2609.11876), [html](https://arxiv.org/html/2609.11876v1), [other](/format/2609.11876)]\n\n\n\nTitle: On the Regularization Landscape for the Linear Recommendation Models\n\n\n\n[Dong Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhenming Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ruoming Jin](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Hao Zhou](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhi Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jing Gao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Bin Ren](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [5] [arXiv:2609.11860](/abs/2609.11860) [[pdf](/pdf/2609.11860), [html](https://arxiv.org/html/2609.11860v1), [other](/format/2609.11860)]\n\n\n\nTitle: Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models\n\n\n\n[Rodion Krjutškov](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Eduard Barbu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Nikos Sakkas](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Sofia Yfanti](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 11 pages, 3 figures. Accepted author version of a paper published at ICECET 2026\n\n\n\nJournal-ref: 2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET), Rome, Italy, 2026\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)\n\n\n\n   [6] [arXiv:2609.11859](/abs/2609.11859) [[pdf](/pdf/2609.11859), [html](https://arxiv.org/html/2609.11859v1), [other](/format/2609.11859)]\n\n\n\nTitle: From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge\n\n\n\n[Wenkang Wei](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yuan Fang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Renhe Jiang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Hong Cheng](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xingtong Yu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 53 pages, 13 figures, including appendices\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [7] [arXiv:2609.11768](/abs/2609.11768) [[pdf](/pdf/2609.11768), [html](https://arxiv.org/html/2609.11768v1), [other](/format/2609.11768)]\n\n\n\nTitle: A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients\n\n\n\n[Suwan Wu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yumeng Lin](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Pengcheng Yuan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiaolong Jiang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: Accepted at the Findings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026 Findings)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)\n\n\n\n   [8] [arXiv:2609.11752](/abs/2609.11752) [[pdf](/pdf/2609.11752), [html](https://arxiv.org/html/2609.11752v1), [other](/format/2609.11752)]\n\n\n\nTitle: SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control\n\n\n\n[Suwan Wu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yumeng Lin](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Pengcheng Yuan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiaolong Jiang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 14 pages, 12 figures. Accepted at the Industry Track of EMNLP 2026\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)\n\n\n\n   [9] [arXiv:2609.11709](/abs/2609.11709) [[pdf](/pdf/2609.11709), [html](https://arxiv.org/html/2609.11709v1), [other](/format/2609.11709)]\n\n\n\nTitle: When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making\n\n\n\n[Ken Chen](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Wei Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Sachith Seneviratne](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Hansani Weeratunge](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Saman Halgamuge](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)\n\n\n\n   [10] [arXiv:2609.11682](/abs/2609.11682) [[pdf](/pdf/2609.11682), [html](https://arxiv.org/html/2609.11682v1), [other](/format/2609.11682)]\n\n\n\nTitle: COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization\n\n\n\n[Pingchen Lu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiangyi Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiang Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jie Mao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zikun Qu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Junfeng Luo](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yao Shu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Bryan Kian Hsiang Low](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhongxiang Dai](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [11] [arXiv:2609.11674](/abs/2609.11674) [[pdf](/pdf/2609.11674), [other](/format/2609.11674)]\n\n\n\nTitle: Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government\n\n\n\n[Danny EBanks](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Devika Jain](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [12] [arXiv:2609.11660](/abs/2609.11660) [[pdf](/pdf/2609.11660), [other](/format/2609.11660)]\n\n\n\nTitle: Autonomy, Social Norms, and Alignment: Towards a Developmental Framework for Autonomous Artificial Agents\n\n\n\n[Marica Notte](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ludovica Marinucci](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Vieri Giuliano Santucci](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: In publication in the proceedings of SIpEIA 2026 conference\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [13] [arXiv:2609.11636](/abs/2609.11636) [[pdf](/pdf/2609.11636), [html](https://arxiv.org/html/2609.11636v1), [other](/format/2609.11636)]\n\n\n\nTitle: MAPLE: Memory-Augmented Planning with Language and Evolution\n\n\n\n[Kesheng Chen](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yamin Hu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Wenjian Luo](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [14] [arXiv:2609.11615](/abs/2609.11615) [[pdf](/pdf/2609.11615), [html](https://arxiv.org/html/2609.11615v1), [other](/format/2609.11615)]\n\n\n\nTitle: Distributed Optimization of Modular Production Systems using Model-based Reinforcement Learning with Inverse Models\n\n\n\n[Andreas Schwung](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Steve Yuwono](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Sofiene Lassoued](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Dorothea Schwung](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY)\n\n\n\n   [15] [arXiv:2609.11607](/abs/2609.11607) [[pdf](/pdf/2609.11607), [html](https://arxiv.org/html/2609.11607v1), [other](/format/2609.11607)]\n\n\n\nTitle: Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting\n\n\n\n[Jihoon Kwon](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Lawrence Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Daekyung Park](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Sumin Kim](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Haverty Jack](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Hoyoung Lee](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Katherine Bjorkman](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Josh McKenney](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Peter Laurelli](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Nicole Kagan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zach Golkhou](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Thorsten Neumann](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Edward Tong](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Pete Petersen](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yoon Kim](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Alejandro Lopez-Lira](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yongjae Lee](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Chanyeol Choi](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 13 pages\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [16] [arXiv:2609.11569](/abs/2609.11569) [[pdf](/pdf/2609.11569), [html](https://arxiv.org/html/2609.11569v1), [other](/format/2609.11569)]\n\n\n\nTitle: Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)\n\n\n\n[Harshdeep Singh](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yurui Zhu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Giovanni Colavizza](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Matteo Romanello](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)\n\n\n\n   [17] [arXiv:2609.11542](/abs/2609.11542) [[pdf](/pdf/2609.11542), [html](https://arxiv.org/html/2609.11542v1), [other](/format/2609.11542)]\n\n\n\nTitle: Characterizing Job Power Elasticity for Power-Flexible AI Training\n\n\n\n[Philip Colangelo](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Charles Dawson](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Shayan Sengupta](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ayse Coskun](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Varun Sivaram](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [18] [arXiv:2609.11532](/abs/2609.11532) [[pdf](/pdf/2609.11532), [html](https://arxiv.org/html/2609.11532v1), [other](/format/2609.11532)]\n\n\n\nTitle: Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems\n\n\n\n[Aleksandra Urman](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Elsa Lichtenegger](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Salima Jaoua](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Azza Bouleimen](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Robin Forsberg](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Corinna Hertweck](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Stefania Ionescu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Nicolò Pagan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ancsa Hannak](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Joachim Baumann](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: Accepted to EMNLP 2026\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [19] [arXiv:2609.11527](/abs/2609.11527) [[pdf](/pdf/2609.11527), [other](/format/2609.11527)]\n\n\n\nTitle: Lightweight LiDAR-Based Cone Detection Framework Using Random Forest for Formula Student Driverless\n\n\n\n[Márk Mező-Kerekes](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Péter Praksz](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Chang Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 9 pages, 2 figures, 3 tables. Accepted at the 5th International Conference on Cognitive Mobility (CogMob 2026)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [20] [arXiv:2609.11509](/abs/2609.11509) [[pdf](/pdf/2609.11509), [html](https://arxiv.org/html/2609.11509v1), [other](/format/2609.11509)]\n\n\n\nTitle: Extending SMT Solving with Non-Ground Clause Learning\n\n\n\n[Yasmine Briefs](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Christoph Weidenbach](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: Extended version of LPAR 2026 paper\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)\n\n\n\n   [21] [arXiv:2609.11498](/abs/2609.11498) [[pdf](/pdf/2609.11498), [html](https://arxiv.org/html/2609.11498v1), [other](/format/2609.11498)]\n\n\n\nTitle: ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps\n\n\n\n[Jacopo Dardini](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D) (University of Bologna), [Roberta Calegari](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D) (University of Bologna)\n\n\n\nComments: 13 pages, 4 figures, 10 tables. Includes technical appendix\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [22] [arXiv:2609.11493](/abs/2609.11493) [[pdf](/pdf/2609.11493), [html](https://arxiv.org/html/2609.11493v1), [other](/format/2609.11493)]\n\n\n\nTitle: From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development\n\n\n\n[Reza Amirmoshiri](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Faryad Sahneh](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yasser Jangjou](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)\n\n\n\n   [23] [arXiv:2609.11490](/abs/2609.11490) [[pdf](/pdf/2609.11490), [html](https://arxiv.org/html/2609.11490v1), [other](/format/2609.11490)]\n\n\n\nTitle: Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints\n\n\n\n[Junlong Shen Xingyu Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 38 pages, 4 figures, 26 tables. Independent of and concurrent with [arXiv:2609.08901](https://arxiv.org/abs/2609.08901) (posted 8 Sep 2026): the instrument and protocol here were pre-registered on 29 Aug 2026; dated provenance in Appendix S\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)\n\n\n\n   [24] [arXiv:2609.11489](/abs/2609.11489) [[pdf](/pdf/2609.11489), [html](https://arxiv.org/html/2609.11489v1), [other](/format/2609.11489)]\n\n\n\nTitle: The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation\n\n\n\n[Makoto Fukushima](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Hua-Dong Xiong](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ehsan Moradi Pari](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)\n\n\n\n   [25] [arXiv:2609.11458](/abs/2609.11458) [[pdf](/pdf/2609.11458), [html](https://arxiv.org/html/2609.11458v1), [other](/format/2609.11458)]\n\n\n\nTitle: Flexible and Interpretable Accent Distance Measurements\n\n\n\n[Charles McGhee](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Mark J. F. Gales](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Kate M. Knill](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [26] [arXiv:2609.11452](/abs/2609.11452) [[pdf](/pdf/2609.11452), [other](/format/2609.11452)]\n\n\n\nTitle: RouteRepair: Instance-Level Failure Diagnosis and Targeted Repair in LLM-Based Automated Heuristic Design for Routing Optimization\n\n\n\n[Binghao Ji](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Di Huang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jiahui Fang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhiyuan Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 22 pages, 13 figures, 11 tables\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [27] [arXiv:2609.11446](/abs/2609.11446) [[pdf](/pdf/2609.11446), [html](https://arxiv.org/html/2609.11446v1), [other](/format/2609.11446)]\n\n\n\nTitle: Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration\n\n\n\n[Yilin Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Han Jiang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Cai Xu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ying Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Wei Zhao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 13 pages, 6 figures, 6 tables, including appendix. Under review\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [28] [arXiv:2609.11431](/abs/2609.11431) [[pdf](/pdf/2609.11431), [html](https://arxiv.org/html/2609.11431v1), [other](/format/2609.11431)]\n\n\n\nTitle: LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study\n\n\n\n[Jorge López-Varela](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [J. Ignacio Hidalgo](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [José-Manuel Muñoz](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Omar Costilla-Reyes](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Esther Maqueda](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jesus Moreno-Fernandez](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Tomás González-Vidal](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [J. Manuel Velasco](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Oscar Garnica](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [29] [arXiv:2609.11403](/abs/2609.11403) [[pdf](/pdf/2609.11403), [html](https://arxiv.org/html/2609.11403v1), [other](/format/2609.11403)]\n\n\n\nTitle: From Queries to Narratives: Cultural Heritage Data Stories for Knowledge Graph Exploration and Quality Assessment\n\n\n\n[Tabea Tietz](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Torsten Schrade](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Etienne Posthumus](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Linnaea Söhn](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jonatan Jalle Steller](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jörg Waitelonis](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Harald Sack](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Digital Libraries (cs.DL)\n\n\n\n   [30] [arXiv:2609.11393](/abs/2609.11393) [[pdf](/pdf/2609.11393), [html](https://arxiv.org/html/2609.11393v1), [other](/format/2609.11393)]\n\n\n\nTitle: Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning\n\n\n\n[Bincheng Gu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Min Gao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zongwei Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yibing Bai](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yulan He](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Junliang Yu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [31] [arXiv:2609.11372](/abs/2609.11372) [[pdf](/pdf/2609.11372), [html](https://arxiv.org/html/2609.11372v1), [other](/format/2609.11372)]\n\n\n\nTitle: RAMamba-Net: A Reliability-Aware and Mamba-Based Multimodal Fusion Network for Auditory Attention Detection\n\n\n\n[Xingyi He](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ziwei Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Dongrui Wu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: RAMamba-Net, a reliability-aware Mamba-based multimodal fusion network for auditory attention decoding\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [32] [arXiv:2609.11365](/abs/2609.11365) [[pdf](/pdf/2609.11365), [html](https://arxiv.org/html/2609.11365v1), [other](/format/2609.11365)]\n\n\n\nTitle: Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells\n\n\n\n[Narcis Marincat](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 17 pages, 1 figure, 5 tables. Companion to [arXiv:2608.20054](https://arxiv.org/abs/2608.20054). Code and evaluation records: [this https URL](https://github.com/tokenosopher/populus-evidence-partitioning) ; checkpoints and fitted alignment maps: [this https URL](https://huggingface.co/tokenosopher/populus-evidence-partitioning-checkpoints)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [33] [arXiv:2609.11341](/abs/2609.11341) [[pdf](/pdf/2609.11341), [html](https://arxiv.org/html/2609.11341v1), [other](/format/2609.11341)]\n\n\n\nTitle: Exploring Diffusion Transformers for Cross-Modal Augmentation in Multimodal Brain State Decoding\n\n\n\n[Ziwei Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xingyi He](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Hongbin Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Tianwang Jia](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Bohan Fang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Dongrui Wu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: CoMA-DiT, a cross-modal augmentation framework built on Diffusion Transformer, extends multimodal learning beyond fusion by leveraging paired modalities as mutual generative supervision to enrich training data and improve brain state decoding\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [34] [arXiv:2609.11321](/abs/2609.11321) [[pdf](/pdf/2609.11321), [html](https://arxiv.org/html/2609.11321v1), [other](/format/2609.11321)]\n\n\n\nTitle: AI Exposure and AI Resilience: A Two-Dimensional Assessment Framework for Software and Software-Based Business Model\n\n\n\n[Paul Darius Mandl](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D) (Findustrial GmbH), [Peter Mandl](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D) (Munich University of Applied Sciences), [Martin Häusl](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D) (Munich University of Applied Sciences)\n\n\n\nComments: 14 pages, 3 figures, 6 tables. Preprint\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [35] [arXiv:2609.11319](/abs/2609.11319) [[pdf](/pdf/2609.11319), [html](https://arxiv.org/html/2609.11319v1), [other](/format/2609.11319)]\n\n\n\nTitle: Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification\n\n\n\n[Joshua Ong Jun Leang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Haonan Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zheng Zhao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xinyi Shang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Wenda Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhengzhong Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Erix Xing](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Shay Cohen](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Eleonora Giunchiglia](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 9 pages, preprint\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [36] [arXiv:2609.11318](/abs/2609.11318) [[pdf](/pdf/2609.11318), [html](https://arxiv.org/html/2609.11318v1), [other](/format/2609.11318)]\n\n\n\nTitle: Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents\n\n\n\n[Minghao Guo](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Meng Cao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Sui Zhao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Siyu Ning](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xin Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Haoze Zhao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jiaxuan Yang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Haihong Hao](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Mingfei Han](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Shunlin Rong](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Haijun Wu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiaodan Liang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiaojun Chang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: Code and data are available at [this https URL](https://github.com/minghaoguo20/Mr-LHDR-eval)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [37] [arXiv:2609.11315](/abs/2609.11315) [[pdf](/pdf/2609.11315), [html](https://arxiv.org/html/2609.11315v1), [other](/format/2609.11315)]\n\n\n\nTitle: Routing by Reasoning Need: Trajectory-Aware Decoding Control for Diffusion Vision-Language Models\n\n\n\n[Yixiang Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhongxing Xu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhonghua Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiaoying Tang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 17 pages, 9 figures. Accepted to Findings of EMNLP 2026\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [38] [arXiv:2609.11294](/abs/2609.11294) [[pdf](/pdf/2609.11294), [html](https://arxiv.org/html/2609.11294v1), [other](/format/2609.11294)]\n\n\n\nTitle: Memory Compression for High-Fanout Agent Sandboxes\n\n\n\n[Mengming Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ceyu XU](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Qijun Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jiangnan Yu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiangfeng Sun](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Haohui Mai](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhiyao Xie](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Operating Systems (cs.OS)\n\n\n\n   [39] [arXiv:2609.11291](/abs/2609.11291) [[pdf](/pdf/2609.11291), [html](https://arxiv.org/html/2609.11291v1), [other](/format/2609.11291)]\n\n\n\nTitle: Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model\n\n\n\n[Hyojung Han](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 19 pages. Korean-language evaluation (KoBBQ); all uncertainty estimates over KoBBQ items are clustered on the benchmark template\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [40] [arXiv:2609.11286](/abs/2609.11286) [[pdf](/pdf/2609.11286), [other](/format/2609.11286)]\n\n\n\nTitle: Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data\n\n\n\n[Benjamin Gruenbaum](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Doron Porat](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Assaf Natanzon](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Roy Zavida](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Chen Dinachi](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Or Itzahary](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Omer Niv](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 10 pages\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [41] [arXiv:2609.11282](/abs/2609.11282) [[pdf](/pdf/2609.11282), [html](https://arxiv.org/html/2609.11282v1), [other](/format/2609.11282)]\n\n\n\nTitle: When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting\n\n\n\n[Emma Andrews](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Gianmarco Mengaldo](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Information Theory (cs.IT)\n\n\n\n   [42] [arXiv:2609.11281](/abs/2609.11281) [[pdf](/pdf/2609.11281), [html](https://arxiv.org/html/2609.11281v1), [other](/format/2609.11281)]\n\n\n\nTitle: Bio-inspired Learning and Decision-Making with Probabilistic In-Memory Computing Hardware: Part 1\n\n\n\n[Thomas Dalgaty](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Eiji Kawasaki](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Miguel de Prado](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Devendra Vyas](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Tommaso Salvatori](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)\n\n\n\n   [43] [arXiv:2609.11277](/abs/2609.11277) [[pdf](/pdf/2609.11277), [html](https://arxiv.org/html/2609.11277v1), [other](/format/2609.11277)]\n\n\n\nTitle: Predicting Train Delays in Finland Using Machine Learning and Weather Data\n\n\n\n[Vinicius Pozzobon Borin](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jean Michel de Souza Sant'Ana](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D'Ana,+J+M), [Nurul Huda Mahmood](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: 6 pages, 3 Figures, 4 tables, presented at Wireless Europe 2026, Rimini, Italy, June 2026\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)\n\n\n\n   [44] [arXiv:2609.11262](/abs/2609.11262) [[pdf](/pdf/2609.11262), [other](/format/2609.11262)]\n\n\n\nTitle: AI-Powered Flare Combustion Efficiency Estimation\n\n\n\n[Afeefa Azam](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Iyyakutti Iyappan Ganapathi](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Fares Ossama Abdelhafez](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Divya Velayudhan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Maregu Assefa Habtie](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Hamad Karki](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Khalid Yousef Al Awadhi](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Naoufel Werghi](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: Accepted at the 4th International Conference on Machine Learning and Data Engineering (ICMLDE 2025). 5 pages\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)\n\n\n\n   [45] [arXiv:2609.11243](/abs/2609.11243) [[pdf](/pdf/2609.11243), [html](https://arxiv.org/html/2609.11243v1), [other](/format/2609.11243)]\n\n\n\nTitle: Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents\n\n\n\n[Jiaqiang Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yajie Yang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhiheng Xi](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jiadong Chen](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Enyu Zhou](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Senjie Jin](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yang Nan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jiazheng Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Han Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yanxin Li](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Dingwei Zhu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Bicheng Deng](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yuhui Wang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xiang Zheng](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Qi Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Lei Bai](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xingjun Ma](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Tao Gui](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [46] [arXiv:2609.11234](/abs/2609.11234) [[pdf](/pdf/2609.11234), [html](https://arxiv.org/html/2609.11234v1), [other](/format/2609.11234)]\n\n\n\nTitle: NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment\n\n\n\n[Guoqiang Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Kexin Tan](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Ming Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Li Ju](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Wenqing Jing](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Zhonghan Yue](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Jiayi Chen](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Shiqiang Wu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Shaofan Liu](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yue Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yuankai Ying](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Yang Shi](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Tao Gui](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Qi Zhang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Xuanjing Huang](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [47] [arXiv:2609.11231](/abs/2609.11231) [[pdf](/pdf/2609.11231), [html](https://arxiv.org/html/2609.11231v1), [other](/format/2609.11231)]\n\n\n\nTitle: A Voice-Interactive Multi-Agent System for Smart Operating Rooms: Architecture Design and Key Technologies\n\n\n\n[Tianxiang Zhou](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)\n\n\n\n   [48] [arXiv:2609.11206](/abs/2609.11206) [[pdf](/pdf/2609.11206), [html](https://arxiv.org/html/2609.11206v1), [other](/format/2609.11206)]\n\n\n\nTitle: CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series Forecasting\n\n\n\n[Yalda Taheri](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Mohammad Hassan Heydari](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Armon Rasooli](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Maryam Amirshahkarami](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Mohammad Ebrahim Mahdavi](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Hossein Karshenas](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)\n\n\n\n   [49] [arXiv:2609.11199](/abs/2609.11199) [[pdf](/pdf/2609.11199), [other](/format/2609.11199)]\n\n\n\nTitle: An AI-Powered Culturally Aware Chatbot for Stress Detection and Wellness Support among Pakistani University Students Using NLP and Machine Learning\n\n\n\n[Muhammad Fahad Bashir](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D), [Muhammad Afzal](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nSubjects: Artificial Intelligence (cs.AI)\n\n\n\n   [50] [arXiv:2609.11190](/abs/2609.11190) [[pdf](/pdf/2609.11190), [other](/format/2609.11190)]\n\n\n\nTitle: Agentic Share-of-Search: A Multi-Agent AI System for Competitive Decision-Making in LLM-Mediated E-Commerce\n\n\n\n[Spandan Ghose Chowdhury](https://arxiv.org/search/cs?searchtype=%5BREDACTED%5D&query=%5BREDACTED%5D)\n\n\n\nComments: Accepted for presentation at the 2026 Decision Science Institute Annual Conference\n\n\n\nSubjects: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)\n\n\n\n\n\nTotal of 1208 entries : 1-50 [51-100](/list/cs.AI/recent?skip=50&show=50) [101-150](/list/cs.AI/recent?skip=100&show=50) [151-200](/list/cs.AI/recent?skip=150&show=50) ... [1201-1208](/list/cs.AI/recent?skip=1200&show=50)\n\n\n\nShowing up to 50 entries per page: [fewer](/list/cs.AI/recent?skip=0&show=25) | [more](/list/cs.AI/recent?skip=0&show=100) | [all](/list/cs.AI/recent?skip=0&show=2000)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n We gratefully acknowledge support from our **major funders**, [**member institutions**](https://info.arxiv.org/about/ourmembers.html), ****, and all contributors.\n\n\n\n [About](https://info.arxiv.org/about) · [Help](https://info.arxiv.org/help) · [Contact](https://info.arxiv.org/help/contact.html) · [Subscribe](https://info.arxiv.org/help/subscribe) · [Copyright](https://info.arxiv.org/help/license/index.html) · [Privacy](https://info.arxiv.org/help/policies/privacy_policy.html) · [Accessibility](https://info.arxiv.org/help/web_accessibility.html) · [Operational Status (opens in new tab)](https://status.arxiv.org)\n\n\n\n\n\n\n\nMajor funding support from\n\n\n\n [![Simons Foundation](/static/base/1.0.1/images/funders/simons-foundation.png)](https://www.simonsfoundation.org/) [![Simons Foundation International](/static/base/1.0.1/images/funders/simons-foundation-international.png)](https://www.sfi.org.bm/) [![Schmidt Sciences](/static/base/1.0.1/images/funders/schmidt-sciences.png)](https://www.schmidtsciences.org/)",
    "content_length": 42096,
    "content_type": "text/html",
    "description": "",
    "status_code": 200,
    "success": true,
    "title": "Artificial Intelligence",
    "url": "https://arxiv.org/list/cs.AI/recent"
  },
  "error": "",
  "elapsed": 0.042644469
}

{
  "tool_name": "send_message",
  "tool_input": {
    "final": true,
    "in_response_to": "b8f07680",
    "message": "Here are the [20 newest cs.AI submissions](https://arxiv.org/list/cs.AI/recent) (all posted Fri, 11 Sep 2026), grouped:\n\n**Agents, autonomy and alignment (6)**\n- Artificial Id: Drive and Persistent Alignment in Agentic AI\n- COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization\n- When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making\n- MAPLE: Memory-Augmented Planning with Language and Evolution\n- Autonomy, Social Norms, and Alignment: Towards a Developmental Framework for Autonomous Artificial Agents\n- The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation\n\n**Foundation model capability and reasoning probes (4)**\n- Can Edge-Deployable Vision-Language Models Identify Species?\n- MindTopo: Can Foundation Models Reason in Topological Space?\n- From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge\n- ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps\n\n**Training, distillation and model auditing (3)**\n- A Unified Per-Token Gating Family for On-Policy Distillation\n- Published Unlearning Numbers Move Per Checkpoint... An Audit of 263 Released Batch-Normalized Checkpoints\n- Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration\n\n**Applied/industrial AI (5)**\n- SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control\n- Distributed Optimization of Modular Production Systems using Model-based RL with Inverse Models\n- Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting\n- Characterizing Job Power Elasticity for Power-Flexible AI Training\n- Lightweight LiDAR-Based Cone Detection Using Random Forest for Formula Student Driverless\n\n**Knowledge, explainability and social impact (4)**\n- Explainability Assistant: A Conversational XAI Interface for Energy Consumption Models\n- Enabling Knowledge Graph Understanding at Scale (EXYGEN)\n- Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government\n- Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems\n\n**Symbolic reasoning (1)**\n- Extending SMT Solving with Non-Ground Clause Learning\n\nMost common direction: making LLM-based agents more reliable, through self-improving memory and skills, multi-agent consensus, uncertainty estimation, and auditing what models actually know. Trust and verification, not raw capability, is the shared thread."
  },
  "dispatch_id": "toolu_01HYi4uKNHwn8ma3AsbVVjCY",
  "parent_dispatch_id": "",
  "handle": "",
  "panel_kind": ""
}

{
  "tool_name": "send_message",
  "dispatch_id": "toolu_01HYi4uKNHwn8ma3AsbVVjCY",
  "status": "completed",
  "result": "Delivered (confirmed) as 3 messages. Your draft was polished into texting register, so the wording differs from what you wrote; this is exactly what the user sees:\n1) Five themes on the 20 newest cs.AI posts: agents and alignment, foundation model reasoning, training and auditing, industrial AI, and knowledge and social impact.\n2) ### cs.AI themes · arxiv papers\n\n| Theme | Papers |\n|-------|--------|\n| Agents, autonomy and alignment | Artificial Id: Drive and Persistent Alignment in Agentic AI; COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization; When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making; MAPLE: Memory-Augmented Planning with Language and Evolution; Autonomy, Social Norms, and Alignment: Towards a Developmental Framework for Autonomous Artificial Agents; The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation |\n| Foundation model capability and reasoning probes | Can Edge-Deployable Vision-Language Models Identify Species?; MindTopo: Can Foundation Models Reason in Topological Space?; From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge; ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps |\n| Training, distillation and model auditing | A Unified Per-Token Gating Family for On-Policy Distillation; Published Unlearning Numbers Move Per Checkpoint... An Audit of 263 Released Batch-Normalized Checkpoints; Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration |\n| Applied/industrial AI | SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control; Distributed Optimization of Modular Production Systems using Model-based RL with Inverse Models; Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting; Characterizing Job Power Elasticity for Power-Flexible AI Training; Lightweight LiDAR-Based Cone Detection Using Random Forest for Formula Student Driverless |\n| Knowledge, explainability and social impact | Explainability Assistant: A Conversational XAI Interface for Energy Consumption Models; Enabling Knowledge Graph Understanding at Scale (EXYGEN); Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government; Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems |\n| Symbolic reasoning | Extending SMT Solving with Non-Ground Clause Learning |\n3) Most common thread: making LLM agents more reliable through self-improving memory, multi-agent consensus, uncertainty estimation, and auditing what models know. Trust and verification matter more than raw capability right now.\nThese are your words now, and this is the whole reply: the delivery layer chose its density and shape by design. Never dispute, re-explain, or apologize for the phrasing, and never send a supplement to restore detail it left out. Only a final send settles its request. Never chase wording with another send. If a fact in it is wrong and would change what the user does, correct it when their next message arrives.\n\nNothing else is open: no request awaits a reply and no work is running. A response with no tool call ends the run.\nanswers: b8f07680-cb84-4b74-92de-6932eabbe234",
  "error": "",
  "elapsed": 23.365676587
}