# EDV：逃离自我确认陷阱的"执行-蒸馏-验证"智能体经验学习框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-23 08:00
- AIHOT 分数：49
- AIHOT 链接：https://aihot.virxact.com/items/cmqrjiayk0kt4slp5e93cjuiu
- 原文链接：https://arxiv.org/abs/2606.24428

## AI 摘要

大语言模型智能体在开放世界交互中自我进化时，单智能体循环易陷入自我确认陷阱——将错误但自洽的轨迹误判为成功，导致错误累积。EDV 框架将经验学习解耦为执行、蒸馏、验证三阶段：多异构智能体并行探索产生多样化轨迹；第三方智能体对比分析减少归纳偏差；执行组通过共识机制验证候选经验，仅批准内容写入记忆。在 tau2-bench、Mind2Web 和 MMTB 三个长周期基准上，EDV 持续超越强基线，验证了可靠经验构建对鲁棒自我演化的关键作用。代码已开源。

## 正文

Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction. However, existing experience learning methods mostly rely on single-agent loops, where the same agent executes tasks, summarizes outcomes, and determines memory content. This setup makes agents vulnerable to the Self-Confirmation Trap: wrong-but-self-consistent trajectories are misidentified as successful experience, leading to cumulative errors during retrieval and reuse. To address this issue, we propose EDV, an Execute-Distill-Verify framework for reliable experience learning. In the Execute stage, multiple heterogeneous agents explore the same task space in parallel to generate diverse candidate trajectories. In the Distill stage, a dedicated third-party agent comparatively analyzes these trajectories to produce candidate experiences, reducing executor-centric summarization bias. In the Verify stage, the execution group validates candidates via a consensus mechanism, and only approved experiences are written into shared or private memory. By decoupling the three stages, EDV transforms experience learning from isolated self-reflection into collaborative construction, filtering erroneous and noisy content before memory insertion. We evaluate EDV on three challenging long-horizon benchmarks: tau2-bench, Mind2Web and MMTB. Results show EDV consistently outperforms strong baselines, validating that reliable experience construction is essential for robust agent self-evolution. Our code is available at https://github.com/shidingz/EDV.