PreFlect：从回顾性到前瞻性反思在大语言模型代理中的应用
PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents
AI总结：
PreFlect通过前瞻性反思机制在执行前改进代理计划，提升复杂任务的性能，优于现有反思方法和更复杂的架构。
摘要：
先进的大语言模型代理通常采用自我反思来提高性能，其中代理迭代分析过去的行为以纠正错误。然而，现有的反思方法本质上是回顾性的：代理行动，观察失败，然后才尝试恢复。在本工作中，我们引入了PreFlect，一种前瞻性反思机制，通过在执行前批评和改进代理计划，将范式从事后修正转变为预执行前瞻性。为了支持基于事实的前瞻性反思，我们从历史代理轨迹中提炼规划错误，捕捉在过去的执行中观察到的反复成功和失败模式。此外，我们通过动态重规划机制补充前瞻性反思，以在原始计划遇到意外偏差时提供执行时的计划更新。在不同基准测试中的评估表明，PreFlect在复杂现实任务上显著提高了整体代理效用，优于强大的基于反思的基线和几种更复杂的代理架构。代码将在https://github.com/wwwhy725/PreFlect中更新。
英文摘要：
Advanced large language model agents typically adopt self-reflection for improving performance, where agents iteratively analyze past actions to correct errors. However, existing reflective approaches are inherently retrospective: agents act, observe failure, and only then attempt to recover. In this work, we introduce PreFlect, a prospective reflection mechanism that shifts the paradigm from post hoc correction to pre-execution foresight by criticizing and refining agent plans before execution. To support grounded prospective reflection, we distill planning errors from historical agent trajectories, capturing recurring success and failure patterns observed across past executions. Furthermore, we complement prospective reflection with a dynamic re-planning mechanism that provides execution-time plan update in case the original plan encounters unexpected deviation. Evaluations on different benchmarks demonstrate that PreFlect significantly improves overall agent utility on complex real-world tasks, outperforming strong reflection-based baselines and several more complex agent architectures. Code will be updated at https://github.com/wwwhy725/PreFlect.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
