MemHarness: Memory Is Reconstructed, Not Replayed
- Published
- Source
- arXiv
- Paper number
- 770
- Field
- AI / General
- arXiv ID
- 2607.28272
Key points
- It applies the human memory principle of reconstruction to AI agents, meaning that past experiences are critically revised and edited to fit the current situation.
- It uses GRPO reinforcement learning to let the agent learn memory reconstruction naturally, without extra human labeling.
- It achieves 85.2 percent on ALFWorld and 75.6 percent on WebShop, outperforming both pure RL and static-memory methods.
- When the memory reconstruction module is removed, performance drops to 74.6 percent, confirming that reconstruction itself is the key contribution.
- Learning to reconstruct memory during training also improves base reasoning ability at inference time even without memory, which the paper calls a latent guidance effect.
Paper links
External research summaries. These are not HDATF publications or measured product results.