English(EN) AT-AT: Automatic Tool Optimization from Agent Traces

新的AT-AT系统利用历史数据优化AI代理工具

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了AT-AT，一个新颖的系统，旨在通过从历史执行轨迹中学习来优化AI代理使用的共享工具。这种方法侧重于通过编辑工具描述和实现来改进工具本身，而不是代理。AT-AT在各种基准测试和实际企业应用中都显著提高了任务完成率并降低了成本，为通过环境侧学习持续增强代理系统提供了一条途径。 AI

影响通过改进AI代理所交互的基础工具，这种方法可能带来更高效、更可靠的AI代理。

排序理由该集群包含一篇详细介绍AI工具优化新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍AI工具优化新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Maya Ravichandran, Pragya Tripathi, Dharamendra Kumar, Adith Swaminathan, Nathan Kallus · 2026-10-28 04:00

AT-AT：基于智能体轨迹的自动工具优化

arXiv:2610.34679v1 Announce Type: new Abstract: Efforts to improve LLM-based agents typically focus on modifying the agent itself, yet success also depends on the environment in which an agent acts. Tools mediate this interaction: a tool's description shapes how an agent calls it…