MemHarness Paper: AI Agents Should Reconstruct Memories, Not Replay Them

anselm · x · 2026-08-02

Existing memory-augmented LLM agents typically inject retrieved past experiences verbatim into the context. This often causes "negative transfer" because the static records misalign with the ever-changing current state.

Inspired by human recall, the MemHarness framework introduces a reconstructive approach. At each decision step, the agent critiques and reconstructs retrieved memories conditioned on the present context to generate grounded guidance before acting. This ability is trained end-to-end using GRPO. Experiments on ALFWorld and WebShop show that MemHarness significantly outperforms pure RL and static memory baselines, demonstrating strong out-of-distribution (OOD) robustness and fundamentally improving the agent's intrinsic reasoning capabilities.

Original post →

More from coding & agent

coding & agent channel →