关键在于接口：评估工具架构如何影响编码智能体行为
The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior
浏览论文内容
中文总结 AI 辅助
该研究通过编码智能体的对照实验，发现工具架构会显著影响智能体行为，不同工具架构在一致性、文件访问量、步骤数等方面表现出不同效果，其中Python CodeAct风格接口性能优异。
中文摘要 AI 辅助
随着大型语言模型不断进步，智能体系统愈发重要，而工具是关键的设计维度，因为它们决定智能体如何访问环境中的信息并采取行动。过往关于智能体工具的研究主要聚焦于扩展智能体的能力，却较少系统关注这些能力如何组织并呈现给模型，我们将后一种设计维度称为工具架构。我们通过仓库级问题修复的对照实验，在三个主体、总计11700条轨迹的设置下，研究编码智能体的工具架构，对比六种工具架构，这些架构在底层信息和操作相似的前提下，仅在组织方式和呈现给模型的形式上存在差异。实验表明，即便工具提供的能力相似，工具架构也会改变智能体行为：与仅具备bash工具的基础架构相比，更结构化的低级接口可将重复尝试的一致性提升至多4.7倍；自然语言搜索能拓展仓库探索范围，使相关文件访问量增加11%以上；Python CodeAct风格的接口在达到相近任务性能的同时，步骤数减少41.6%，令牌使用量降低56.3%。相比之下，轻量型文本认知支架工具（如让智能体记录中间推理的工具）对主体行为的影响有限。
英文摘要
As large language models continue to improve, agentic systems are becoming increasingly important, and tools are a key design dimension because they determine how agents access information and take action in their environments. Prior work on agent tooling has primarily focused on expanding what agents can do, but has paid less systematic attention to how those capabilities are organized and exposed to the model. We refer to this latter design dimension as tool architecture. We study tool architecture in coding agents through controlled experiments on repository-level issue fixing, comparing six tool architectures that hold the underlying information and actions similar while varying how they are organized and exposed to the model, across three actors and a total of 11,700 trajectories. Our experiments show that, even when tools provide similar capabilities, tool architecture changes agent behavior: Compared to a basic architecture where the agent has only the bash tool, more structured low-level interfaces improve consistency across repeated attempts by up to 4.7 $\times$; natural-language search broadens repository exploration and increases access to relevant files by more than 11%; and Python CodeAct-style interfaces achieve similar task performance with 41.6% fewer steps and 56.3% lower token usage. By contrast, lightweight text-based cognitive-scaffolding tools, such as tools that let the agent record intermediate reasoning, have limited effect on actor behavior.
