检测智能体轨迹中的冗余步骤，提升推理效率
Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories
- 构建标注轨迹数据集，定义冗余步骤的判定标准
- 最佳方法仅24.88%准确率，远低于随机水平
- 适合关注智能体效率与可解释性的研究者
基于大模型的智能体在复杂任务中展现出强大的多步推理与工具使用能力。然而，现有评估体系主要关注任务成功率，忽略了行为执行效率这一关键问题。实际中，智能体轨迹常包含大量冗余步骤，消耗资源却对任务完成贡献甚微。本文首次提出并定义「冗余步骤检测」这一新研究方向，构建了红冗余性基准测试数据集RedundancyBench，涵盖多样化任务及精细标注的轨迹，每一步均根据其对任务完成的贡献进行标记。利用该数据集，我们评估了三种代表性方法，结果表明即使表现最好的方法也仅达到24.88%的检测准确率，部分方法甚至劣于随机猜测。这揭示了该任务的高难度，凸显了进一步研究的必要性。
原文摘要 · Abstract (English)
LLM-based agents have demonstrated strong capabilities in solving complex tasks through multi-step reasoning and tool use. However, existing evaluation protocols primarily focus on task success, overlooking a critical aspect of agent behavior: execution efficiency. In practice, agent trajectories often contain redundant steps that consume substantial resources while contributing little to task completion. In this work, we propose and formulate a new research area: \textbf{redundant step detection} for agent trajectories. To support this initiative, we introduce \textbf{RedundancyBench}, a new benchmark that contains diverse tasks with carefully annotated trajectories, where each step is labeled according to its contribution to task completion. Using RedundancyBench, we develop and evaluate 3 representative methods to answer whether a step within trajectory is redundant or necessary. Our results show that even the best-performing method achieves only 24.88\% score in detecting redundant steps, while some methods perform worse than random guessing. These results highlight the task's complexity and the need for further research in this area. \footnote{Code and dataset in this paper are both available in \href{https://anonymous.4open.science/r/RedundancyBench}{https://anonymous.4open.science/r/RedundancyBench}.}
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。