cs.CVNov 7, 2026

From Reflection to Co-Evolution: Self-Evolving Agents with Locally Verified Memory

Authors: Xinxiang Yin, Xinglang Zhang, Haodong Chen, Zhiqing Cui, Weidong Tang, Yuxuan Wang, Junrui Wang, Jingyi Zhang, 

Organizations: The University of Hong Kong · Huazhong University of Science and Technology · The Hong Kong University of Science and Technology · National University of Singapore · 

Abstract

LLM agents have made impressive progress in coding and mathematical reasoning, motivating growing interest in learning from long-horizon interaction. Memory supports this process, but plausible lessons can be redundant or reinforce inappropriate actions. Can a memory's source decision provide a practical test for whether to retain it? We localize consequential trajectory steps, extract candidate memories, and replay each source decision with and without its candidate under the same context. This reveals two properties: most candidates barely shift the probed distribution, and both successful and failed source actions can be reinforced or suppressed. These observations motivate Anchor, which tests shift magnitude and source-role alignment before retention. Admitted memories guide later trajectories, enabling experience-driven improvement under a frozen policy. On held-out ALFWorld and WebShop tasks, Anchor improves success rate and mean score by up to 19.9% and 17.2%, respectively, relative to the strongest baseline for each backbone. With Qwen3.5-27B, it retains 41% fewer ALFWorld cards than unfiltered retention and outperforms all four WebShop cost-comparison baselines while using fewer tokens.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Selective Memory Retention for Long-Horizon LLM Agents

    Jun 28, 2026Pranath ReddyLLM Agent MemoryPersistent Memory for Language Models

  2. Remember Before You're Asked: MemDream for Self-Probing Memory Evolution

    Sep 28, 2026Mingfei Lu, Mengjia Wu, Runsong Jia +2LLM Agent MemoryGraph-Based Agent Memory

  3. Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents

    Aug 21, 2026Quang Dao, Purvi Kathalkar, Kenneth EatonLLM Agent MemoryMemory Management for LLM Agents