让大模型提前预判错误，优化计划再执行
PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents
- 提出前瞻式反思机制，先批评计划再执行
- 在复杂任务上性能超越主流基线，提升整体智能体效用
- 适合需要高可靠性规划的AI系统研发人员
先进大模型智能体通常采用自我反思以提升性能，但现有方法均为事后纠正：先执行，发现失败后才尝试修复。本文提出PreFlect，一种前瞻性反思机制，通过在执行前批判和优化计划，将反思从事后修正转向事前预见。为实现有依据的前瞻反思，我们从历史智能体轨迹中提炼出规划错误，捕捉反复出现的成功与失败模式。此外，引入动态重规划机制，在执行过程中应对意外偏差时可实时更新计划。在多个基准测试上的评估表明，PreFlect显著提升了复杂现实任务中的智能体整体效用，优于强基线反射方法及更复杂的智能体架构。代码将在https://github.com/wwwhy725/PreFlect更新。
原文摘要 · Abstract (English)
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.
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。