PulseAugur
中
实时 16:28:06
English(EN) Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

新方法提升AI代理的可靠性和安全性

作者 PulseAugur 编辑部 · [7 个来源] ·

研究人员开发了新方法来提高AI代理的可靠性和安全性。一种名为TRACE的方法侧重于监控长时程代理轨迹，通过分析跨越时间上遥远动作的证据来检测恶意或意外行为。另一种方法，回顾式约束优化（RHO），利用过去的轨迹进行自我监督，并在没有外部验证的情况下改进代理对技能和工具的约束。此外，HarnessFix旨在通过分析执行跟踪并将失败映射到特定约束层进行有针对性的修补，来诊断和修复代理约束中的缺陷。 AI

影响 这些进展旨在通过提高AI代理处理复杂任务和避免意外后果的能力，使其更加健壮、可靠和安全。

排序理由 多篇研究论文介绍了用于改进LLM代理的新框架和方法。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →

新方法提升AI代理的可靠性和安全性

报道来源 [7]

  1. arXiv cs.AI TIER_1 English(EN) · Vijitha Mittapalli, Shreyaa Jayant Dani, Satya Srujana Pilli, Snigdha Ansu, Mohammadreza Teymoorianfard, Franck Dernoncourt, Hongjie Chen, Yu Wang, Ryan A. Rossi, Nesreen K. Ahmed ·

    TRACE：通过自适应跨步证据聚合实现LLM代理的轨迹推理

    arXiv:2606.07054v1 Announce Type: cross Abstract: Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring. Existing approaches either evaluate com…

  2. arXiv cs.CL TIER_1 English(EN) · Nesreen K. Ahmed ·

    TRACE：通过自适应跨步证据聚合实现LLM代理的轨迹推理

    Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring. Existing approaches either evaluate complete trajectories in a single pass or partition t…

  3. arXiv cs.CL TIER_1 English(EN) · Wenbo Pan, Shujie Liu, Chin-Yew Lin, Jingying Zeng, Xianfeng Tang, Xiangyang Zhou, Yan Lu, Xiaohua Jia ·

    回顾性约束优化：通过轨迹回放的自我偏好改进LLM代理

    arXiv:2606.05922v1 Announce Type: cross Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-trut…

  4. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Qing Wang ·

    从失败的轨迹到可靠的LLM代理：诊断和修复Harness缺陷

    LLM-based agents increasingly rely on harnesses that provide execution environments, tool interfaces, context, lifecycle orchestration, observability, verification, and governance. Existing self-improving agents and automatic harness evolution methods mainly improve agents throug…

  5. Hugging Face Daily Papers TIER_1 English(EN) ·

    回顾性约束优化：通过轨迹回放的自我偏好改进LLM代理

    AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-truth validation sets, yet such labeled data is diffic…

  6. arXiv cs.CL TIER_1 English(EN) · Xiaohua Jia ·

    回顾性约束优化：通过轨迹回放的自我偏好改进LLM代理

    AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-truth validation sets, yet such labeled data is diffic…

  7. dev.to — LLM tag TIER_1 English(EN) · sijan gautam ·

    我如何为LLM代理构建意图漂移检测器

    <h2> The Problem </h2> <p>AI agents fail silently.</p> <p>You give an agent a clear instruction:<br /> "Refund user 123, $50 within 7 days"</p> <p>The agent returns:<br /> "User refunded $500 immediately"</p> <p>No error. No warning. Just wrong output.</p> <p>This is <strong>sema…

相关实体

相关话题