hackernews: 正常(20 条) github: 正常(20 条) arxiv: 正常(20 条) arxiv-rss: 正常(20 条)
  1. #1 morluto/rea 100.0
    github · · morluto

    Reverse engineer anything with agents, from app behavior down to native binaries.

  2. hackernews · · pcompeau
  3. github · · openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

  4. hackernews · · samk3nny
  5. github · · obra

    An agentic skills framework & software development methodology that works.

  6. hackernews · · lode
  7. github · · NousResearch

    The agent that grows with you

  8. hackernews · · cwaffles
  9. hackernews · · burntsushi
  10. hackernews · · geerlingguy
  11. hackernews · · PaulHoule
  12. arxiv-rss · · Xintong Wang, Haihan Nan, Ruidong Li

    arXiv:2611.17680v1 Announce Type: new Abstract: Artificial Intelligence of Things (AIoT) systems increasingly combine sensed time series with external text such as expert reports and news, yet how reliably models use text that agrees or conflicts with the sensed history remains unclear. We introduce the first real-world diagnostic benchmark organized by text-history relationship: 1,762 text-window pairs across sensor telemetry (Weather), web-service traffic (Wikipedia), and market data streams (…

  13. arxiv-rss · · You-Lin Chen, Xinyi Lisa Chen, Pedro Herrero-Vidal, Xiaojing Yu, Bingqing Song, Bin Xu

    arXiv:2611.17662v1 Announce Type: new Abstract: Autonomous agents now run for hundreds of steps with little or no human supervision. In practice, practitioners use runtime monitors such as turn limits and keyword filters to decide when a run should be stopped, upgraded, or assisted. However, these heuristics may stop runs that would otherwise succeed or allow failing runs to continue. To address this limitation, we introduce LeBet (Learn then Bet), a statistical learning framework that derives i…

  14. arxiv-rss · · Yue Zhao, Angela Huyue Zhang, S. Alex Yang, Hua Wei, Xiyang Hu

    arXiv:2611.17639v1 Announce Type: new Abstract: Before an LLM agent cancels a reservation or deletes a folder for a user, what stops it from acting on a false assumption: what its tools show, or what the user says? In this work, we study this gap with presupposition theory from linguistics: an agent may act only if each claim behind the act (e.g., one reservation fits the name) is seen to hold, answered by the user, or disclosed while the act can be undone. A simple bound shows that when lookups…

  15. arxiv-rss · · Pulkit Yadav

    arXiv:2611.17632v1 Announce Type: new Abstract: Generating an evaluation suite from an agent's specification is diversity-driven search: a generator fills a descriptor space (requirements $\times$ personas $\times$ scenario kinds), and the suite it emits is an archive, then scored like a benchmark by its mean pass rate, which throws away the search's product. We inject 7 controlled defects into a $\tau^2$-bench agent across two domains. Coverage yields a ceiling: if a defect's traced footprint h…

  16. arxiv-rss · · AI Training Platform Team, Bingwei Zhang, Jing Li, Amir Abdullin, Sihang Chen, Xin Chen, Liangjun Feng, Yingmeng Gao, Tao Guo, Junjie Huang, Dongfang Li, Zhanglian Lin, Jiajun Liu, Zekun Liu, Zhengxuan Lu, Xiaodong Luo, Jian Meng, Ivan Nosov, Linyuan Qiu, Weijian Sun, Wanrui Yan, Binfan Zheng, Zhicheng Zhou, Baotian Hu, Min Zhang, Haizhou Li, Zhiquan Luo

    arXiv:2611.17621v1 Announce Type: new Abstract: Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to optimize existing implementations under input configurations drawn from real workloads. To address this requirement, we introduce AscendGYM, a benchmark whose initial suite comprises 48 kernels across three difficulty le…

  17. arxiv-rss · · Sabrina Tang, Nikolai Vo, Carson Murillo, Chira Sukumarnpiti, Sarah Wilson

    arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference time, subtracting the vector during generation, or through preventative steering, adding the vector during fine-tuning, so the optimizer never needs to encode the trait in weights, then removing the vector at evaluation. C…

  18. arxiv-rss · · Himanshu Kulkarni, Siddharth Krishnamurthy, Jianhong Xin

    arXiv:2611.17616v1 Announce Type: new Abstract: Behavioral clusters learned over user or item interactions drift as behavior evolves: some fragment into sub-behaviors, some converge, some disappear, and new patterns emerge. Two paradigms dominate the maintenance of evolving clusterings. Threshold triggers fire a pre-specified action when a hardcoded statistic crosses a cutoff; refit-and-track (MONIC-style) re-clusters every window and infers transitions from how the new clusters align with the p…

  19. arxiv-rss · · Seyed Mahmoud Sajjadi Mohammadabadi

    arXiv:2611.17610v1 Announce Type: new Abstract: Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This practice confounds coordination with sample multiplicity and inference compute. We synthesize nine primary empirical evaluations comprising 516 unique multi-agent configurations organized along a resource vector R with six dimensions and a baseline ladder with four categories. Against baselines with a single pass (Category A), mul…

  20. arxiv-rss · · Aleksandr M. Shtraukh-Adamsky, Vladimir M. Adamsky, Irina G. Voloshina, Artemiy D. Spitsyn

    arXiv:2611.17583v1 Announce Type: new Abstract: A representation that retains one bit about a four-state world can solve a task perfectly, while another that retains 1.5 bits on average reaches only 75% accuracy. The difference lies in which distinctions each representation preserves. We examine this relationship in a uniform four-state world by enumerating all admissible representations and binary action rules. Constructions are compared both by replacing one component while holding the others…