HyperAgent让代码代理像人一样全流程解决各类编程任务。
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
- 构建四角色协作系统，模拟人类开发者全流程开发
- 在SWE-Bench等5个基准上超越现有最优模型
- 适合需要跨语言、全链路自动化编码的工程团队
大型语言模型（LLMs）已彻底改变软件工程领域，在多种编码任务中展现出卓越能力。尽管近期进展使基于LLM的自主代码代理能够完成端到端开发任务，但这些系统通常仅针对特定软件工程功能设计。本文提出HyperAgent，一种创新的通用多代理系统，通过模仿人类开发者的流程，可处理跨多种编程语言的广泛软件工程任务。该系统包含四个专业化代理：规划者（Planner）、导航者（Navigator）、代码编辑器（Code Editor）和执行者（Executor），可覆盖从初始规划到最终验证的完整开发周期。HyperAgent在多个基准上树立新标准，包括在著名的SWE-Bench基准上解决GitHub问题，表现优于强基线模型；同时在仓库级代码生成（RepoExec）和缺陷定位与程序修复（Defects4J）任务中也显著超越现有最佳水平。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent system designed to tackle a wide range of SE tasks across different programming languages by mimicking the workflows of human developers. HyperAgent features four specialized agents-Planner, Navigator, Code Editor, and Executor-capable of handling the entire lifecycle of SE tasks, from initial planning to final verification. HyperAgent sets new benchmarks in diverse SE tasks, including GitHub issue resolution on the renowned SWE-Bench benchmark, outperforming robust baselines. Furthermore, HyperAgent demonstrates exceptional performance in repository-level code generation (RepoExec) and fault localization and program repair (Defects4J), often surpassing state-of-the-art baselines.
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。