代码智能体可自我修改，提升编程任务表现
A Self-Improving Coding Agent
- 通过自我反思和代码更新实现非梯度优化
- SWE Bench验证集性能提升17%至53%
- 适合研究自主智能体与代码生成的开发者
大型语言模型（LLMs）的进展推动了将LLM智能体部署于真实世界任务。在智能体系统中，代码协调LLM调用并提供工具。我们展示，配备基础编码工具的智能体系统可自主编辑自身代码，从而提升基准任务表现。在随机选取的SWE Bench Verified子集上，性能提升17%至53%，在LiveCodeBench及合成生成的智能体基准测试中也获得额外提升。本工作推进了智能体系统的自动化与开放式设计，展示了由LLM反思驱动、无需梯度的高效学习机制。
原文摘要 · Abstract (English)
Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We demonstrate that an agent system, equipped with basic coding tools, can autonomously edit itself, and thereby improve its performance on benchmark tasks. We find performance gains from 17% to 53% on a random subset of SWE Bench Verified, with additional performance gains on LiveCodeBench, as well as synthetically generated agent benchmarks. Our work represents an advancement in the automated and open-ended design of agentic systems, and demonstrates a data-efficient, non gradient-based learning mechanism driven by LLM reflection and code updates.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。