首次揭示编码代理框架演进如何影响性能，而非大模型本身。
Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality
- 固定大模型，只变代理框架，对比35个版本质量变化。
- 发现框架更新后性能波动剧烈，部分版本效率下降40%以上。
- 适合关注代码生成系统稳定性的开发者与研究者。
编码代理是利用大语言模型（LLM）完成软件工程任务的自主系统，依赖代理框架（agent harness）作为中介层，协调提示设计、工具调用、上下文管理及迭代推理。尽管代理框架演进速度极快，但尚无研究分析其对代理质量（有效性与效率）的影响。从业者常将性能下降归因于模型，而非框架。本文首次开展受控纵向研究，固定模型仅改变代理框架，评估35个连续版本在SWE-bench Verified上的表现。我们分析了五个主流开源框架（Codex、Qwen Code、Gemini、OpenCode、OpenHands）的演化，发现其发布速度超过每日两版，数月内积累数千个问题。针对Qwen Code CLI的深度测试表明，不同版本在50个分层验证任务中表现差异显著，部分版本效率下降超40%。通过追溯具体代码提交，我们揭示了架构组件与开发模式对质量波动的关键影响。
原文摘要 · Abstract (English)
Coding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agent harness: a middleware layer in between a developer and a large language model that orchestrates system prompts, tool execution, context management, and iterative reasoning loops. While these agent harnesses evolve at extreme velocities, no study has examined how this evolution affects agent quality (i.e., effectiveness and efficiency) over time. Practitioners regularly report quality regressions after agent harness updates, yet consistently attribute them to the underlying model rather than the harness itself. In this paper, we address this gap by conducting the first controlled longitudinal study that isolates the agent harness contribution. Unlike prior work that fixes the agent harness and varies the model, we fix the model and vary only the agent harness, evaluating 35 sequential releases to measure their impact on agent effectiveness and efficiency. We first empirically study the development and release evolution of five major open-source agent harnesses (i.e., Codex, Qwen Code, Gemini, OpenCode, and OpenHands), revealing extreme release velocities exceeding two releases per day and thousands of issues within months. We then perform a controlled deep dive into 35 sequential releases of the Qwen Code CLI, evaluating each against 50 stratified SWE-bench Verified tasks while holding the underlying LLM constant. We trace the resulting quality fluctuations to specific development patterns and architectural components, and illustrate our findings with concrete qualitative evidence linking individual pull requests to measured quality shifts.
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。