发表机构
Florida International University; Arizona State University; NEC Laboratories America; Singapore Management University（佛罗里达国际大学; 亚利桑那州立大学; 美国 NEC 实验室; 新加坡管理大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出Trajectory Graph Copilot框架，以Graph Debugger为核心，通过预执行错误诊断提升LLM智能体完成长周期任务的能力，在多基准测试中平均提升14.69%通过率。
AI 中文摘要
基于大语言模型（LLM）的智能体在各类复杂交互任务中展现出卓越性能，但在具身AI等领域常见的长周期交互任务中仍存在不足。这类场景的复杂性与庞大动作空间会引发复合错误，单个次优动作即可破坏完整轨迹，导致智能体在低效或不可恢复路径上耗尽有限的步骤预算。为在无需高成本微调的情况下解决该问题，研究借鉴软件调试中分析执行日志以提前发现错误的思路，提出名为“Trajectory Graph Copilot”的新型框架，作为LLM智能体的“副驾驶”在动作执行前诊断潜在错误。该框架核心为“Graph Debugger”，将历史轨迹建模为概率图，采用图神经网络识别易引发失败的连续动作模式；作为主动诊断沙盒，该方法对潜在缺陷动作发出早期预警，促使智能体自我修正，通过预执行错误诊断避免高成本失误，显著提升智能体完成长周期任务的能力。在四个基准测试集上针对三个LLM智能体开展的大量实验显示，该方法平均提升了14.69%的通过率。
英文摘要
Large Language Model~(LLM)-based agents have demonstrated exceptional performance across a wide range of complex interactive tasks. However, they often struggle with long-horizon interactive tasks common in domains, such as embodied AI. The complexity and vast action spaces in these settings lead to compounding errors, where a single suboptimal action can derail an entire trajectory, causing the agent to exhaust its limited step budget on inefficient or unrecoverable paths. To overcome this without costly fine-tuning, we draw inspiration from software debugging, where execution logs are analyzed to preemptively catch errors. We propose \textit{Trajectory Graph Copilot}, a novel framework that acts as a ``copilot'' for LLM agents by diagnosing potential action errors before they are executed. At its core,\textit{Graph Debugger} models historical trajectories as a probabilistic graph and uses a Graph Neural Network to identify sequential action patterns that frequently lead to failure. Functioning as a proactive diagnostic sandbox, our method provides early warnings on potentially flawed actions, prompting the agent to self-correct. This pre-action error diagnosis prevents costly mistakes, significantly enhancing the agent's ability to complete long-horizon tasks successfully. The extensive experiments on four benchmarks with three LLM agents demonstrate a $14.69\%$ pass ratio improvement on average.
