给AI多智能体系统加了版本控制，让调试和实验更可靠。
AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems
- 借鉴Git思想，支持智能体工作流的提交、回滚和分支
- 在论文摘要分析任务中减少冗余计算，降低30%以上运行时和耗token量
- 适合需要迭代调试、A/B测试或安全探索的AI协作系统研发
随着大语言模型（LLMs）的快速发展，基于LLM的多智能体系统（MAS）在学术界和工业界日益受到关注。然而，现有许多MAS框架在复杂任务上仍面临可靠性与可扩展性挑战。本文提出AgentGit，一个为MAS工作流引入类似Git的提交、回滚与分支能力的框架。该框架构建于LangGraph之上，支持状态提交、回滚与分支，使智能体能高效遍历、对比和探索多条执行轨迹。为评估其效果，我们设计了一个多步A/B测试，通过优化目标智能体的提示词，在真实任务——论文摘要检索与分析上，与三个基线（LangGraph、AutoGen、Agno）进行对比。结果表明，AgentGit显著减少了冗余计算，降低了运行时间和令牌使用量，并支持跨多个分支的并行探索，有效提升了MAS开发中的可靠性与可扩展性。本工作为构建更鲁棒的MAS提供了实用路径，支持错误恢复、安全探索、迭代调试与A/B测试。
原文摘要 · Abstract (English)
With the rapid progress of large language models (LLMs), LLM-powered multi-agent systems (MAS) are drawing increasing interest across academia and industry. However, many current MAS frameworks struggle with reliability and scalability, especially on complex tasks. We present AgentGit, a framework that brings Git-like rollback and branching to MAS workflows. Built as an infrastructure layer on top of LangGraph, AgentGit supports state commit, revert, and branching, allowing agents to traverse, compare, and explore multiple trajectories efficiently. To evaluate AgentGit, we designed an experiment that optimizes target agents by selecting better prompts. We ran a multi-step A/B test against three baselines -- LangGraph, AutoGen, and Agno -- on a real-world task: retrieving and analyzing paper abstracts. Results show that AgentGit significantly reduces redundant computation, lowers runtime and token usage, and supports parallel exploration across multiple branches, enhancing both reliability and scalability in MAS development. This work offers a practical path to more robust MAS design and enables error recovery, safe exploration, iterative debugging, and A/B testing in collaborative AI systems.
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。