News for 2026-05-25

52 items that day

  1. ·arXiv AI

    ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization

  2. ·arXiv AI

    PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning

  3. ·arXiv AI

    The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems

  4. ·arXiv AI

    BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems

  5. ·arXiv AI

    NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Temporal Logic

  6. ·arXiv AI

    RMA: an Agentic System for Research-Level Mathematical Problems

  7. ·arXiv AI

    SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research

  8. ·arXiv AI

    Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems

  9. ·arXiv AI

    Mediative Fuzzy Logic: From Type-1 Foundations to Type-2, Type-3 and Quantum Extensions

  10. ·arXiv AI

    EVE-Agent: Evidence-Verifiable Self-Evolving Agents

  11. ·量子位

    Claude 通过率不到4%,SaaS-Bench撕碎了Computer-Use的「全自动办公」幻想

  12. ·RadarAI

    Claude 通过率不到 4%,SaaS-Bench 撕碎了 Computer-Use 的「全自动办公」幻想

  13. ·RadarAI

    #552. AI 进展为何突然变得真实:详解 GPT 5.5、强化学习与模型最后一公里

  14. ·RadarAI

    74.与地瓜、阿里云的访谈:机器人爆发前夜,工程师成长,与 AI 的第三朵云

  15. ·RadarAI

    让 AI 自己做增长:基于 OPC 和 Harness 思想的自主增长系统探索

  16. ·RadarAI

    E238|聊聊 Harness 时代 AI-First 的组织架构:从信任人到信任 AI

  17. ·Hugging Face Blog

    Harness, Scaffold, and the AI Agent Terms Worth Getting Right

  18. ·OpenAI

    OpenAI, Grupo Folha and Grupo UOL announce strategic content partnership

  19. ·美团技术团队

    从高拟真到真可用,LongCat-Video-Avatar 1.5 正式开源

  20. ·RadarAI

    优化搜索广告:平衡变现与信任的关键抉择

  21. ·TechCrunch AI

    Everyone is navigating AI security in real time — even Google

  22. ·Towards Data Science

    The Ultimate Beginners’ Guide to Building an AI Agent in Python

Previous pagePage 2 / 2

Back to the monthly archive