提出TIDE框架，诊断大模型智能体在测试时如何通过交互改进性能
TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents
- 将测试时改进拆解为时间动态、循环行为、记忆负担三维度
- 发现性能瓶颈常来自无效循环或记忆过载，而非推理能力不足
- 适用于评估各类自主智能体，帮助优化人机交互策略
近期自主大模型智能体展现出通过与环境迭代交互提升性能的能力，我们称此为测试时改进（TTI）。然而，其成功或失败的机制仍不清晰，现有评估指标无法捕捉任务优化效率、错误后行为适应性以及工作记忆对任务完成的具体作用。为此，我们提出测试时改进诊断评估（TIDE）框架，该框架不依赖特定智能体或环境，将TTI分解为三个相互关联的维度：（1）任务完成的整体时间动态；（2）判断性能是否主要受递归循环行为限制；（3）判断是否因累积记忆过重而受限。在多种智能体和环境上的广泛实验表明，提升性能不仅需要增强内部推理，更需显式优化智能体与环境的交互动态。
原文摘要 · Abstract (English)
Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time Improvement (TTI). However, the mechanisms under how and why TTI succeed or fail remain poorly understood, and existing evaluation metrics fail to capture their task optimization efficiency, behavior adaptation after erroneous actions, and the specific utility of working memory for task completion. To address these gaps, we propose Test-time Improvement Diagnostic Evaluation (TIDE), an agent-agnostic and environment-agnostic framework that decomposes TTI into three comprehensive and interconnected dimensions. The framework measures (1) the overall temporal dynamics of task completion and (2) identifies whether performance is primarily constrained by recursive looping behaviors or (3) by burdensome accumulated memory. Through extensive experiments across diverse agents and environments, TIDE highlights that improving agent performance requires more than scaling internal reasoning, calling for explicitly optimizing the interaction dynamics between the agent and the environment.
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。