返回全部动态
DocsChisel：面向LLM代理的自适应工具文档优化框架
原标题：DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents
AI 摘要
该研究对LLM代理的工具文档进行了大规模实证分析，发现不同信息字段的效果因任务领域、LLM骨干和代理范式而异。为此，作者提出DocsChisel框架，通过分析失败轨迹并迭代增删或优化信息字段，将任务成功率较原始文档提升95.89%，较现有基线平均提升75.15%。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
DocsChisel: Adaptive Tool Documentation Optimization Framework for LLM Agents Abstract Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical grounding resource for LLM agents. Existing studies mainly focus on improving the tool-use capabilities of LLM agents, while largely treating tool documentation as a fixed input. Although several recent works attempt to optimize tool documentation through rewriting or co
发布时间：2026-08-12 12:00
抓取时间：2026-08-12 12:09
来源机构：arXiv