上海AI Lab团队推出MemHarness：让Agent记忆像人类一样被重构
Ranking
Overall
83
Content
90
Popularity
65
Observed public metrics from 1 member.
Merged summary
TL;DR - MemHarness is an LLM-agent framework that evaluates and rewrites retrieved experiences for the current context before acting. This reduces harmful transfer from stale memories and improves decision-making, particularly in out-of-distribution settings.
- Adds explicit retrieval, critique/reconstruction, and action-generation stages instead of injecting memories unchanged.
- Trains the full workflow end-to-end with GRPO using task rewards and format constraints, without reconstruction labels.
- Outperforms pure-RL and static-memory baselines on ALFWorld and WebShop; removing reconstruction erases much of the gain.
- Experiments indicate that source/current-state compatibility determines whether memories should be retained, rewritten, or discarded.
Sources (1)
上海AI Lab团队推出MemHarness：让Agent记忆像人类一样被重构
Public signals
Hugging Face upvotes 17
TL;DR - MemHarness is an LLM-agent framework that evaluates and rewrites retrieved experiences for the current context before acting. This reduces harmful transfer from stale memories and improves decision-making, particularly in out-of-distribution settings.
- Adds explicit retrieval, critique/reconstruction, and action-generation stages instead of injecting memories unchanged.
- Trains the full workflow end-to-end with GRPO using task rewards and format constraints, without reconstruction labels.
- Outperforms pure-RL and static-memory baselines on ALFWorld and WebShop; removing reconstruction erases much of the gain.
- Experiments indicate that source/current-state compatibility determines whether memories should be retained, rewritten, or discarded.