MemHarness 让智能体把旧经验改写到当前场景再用，在 ALFWorld 和 WebShop 上比静态记忆基线强不少。
MemHarness 框架在决策时用统一策略模型批判并重构检索到的经验，而不是像基线那样逐字回放。重构能力通过 GRPO 端到端训练自然涌现，无需额外监督。在 ALFWorld 和 WebShop 两个基准上，MemHarness 显著超过纯 RL 和静态记忆增强基线。分析表明，MemHarness 的重构目标可防止负迁移，并在 OOD 场景中保持鲁棒性。
MemHarness: Memory Is Reconstructed, Not Replayed
Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as static records to be replayed verbatim, injecting them into the context regardless of whether they align with the agent's current situation. This ``replay'' paradigm ignores the gap between the abstract, general nature of stored experience and the concrete, ever-changing states encountered at decision time, frequently causing negative transfer. In contrast, humans rarely recall past experiences verbatim; instead, they reorganize and adapt retrieved memories to fit the present context. Inspired by this, we propose MemHarness, a framework that equips LLM agents to actively harness and reconstruct past experiences based on the present context. At each decision step, a unified policy model critiques and reconstructs the retrieved experience conditioned on the current state, producing context-grounded guidance before acting. This reconstructive ability emerges naturally through end-to-end training with GRPO. Experiments on ALFWorld and WebShop show that MemHarness substantially outperforms pure RL and static memory-augmented baselines, demonstrating strong robustness in out-of-distribution (OOD) scenarios. Furthermore, our analyses reveal that this reconstruction objective not only prevents negative transfer but also serves as latent guidance during training, fundamentally improving the agent's intrinsic reasoning capabilities.