| title | Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning |
|---|---|
| authors | Shiding Zhu, Yudi Qi, Yajie Wang, Jiaze Li, Chao Song, Yaorui Shi, Yibo Miao, Hanqi Gao, Kai Zhang |
| date | 2026-06-23 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.24428 |
| affiliation | Zhejiang University |
| upvotes | 15 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | 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. |
cite
@misc{zhu2026escaping,
title={Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning},
author={Shiding Zhu and Yudi Qi and Yajie Wang and Jiaze Li and Chao Song and Yaorui Shi and Yibo Miao and Hanqi Gao and Kai Zhang},
year={2026},
eprint={2606.24428},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.24428}
}