Ruiyi Ding
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Metacognitive Memory Policy Optimization (MMPO), a novel memory training approach that optimizes LLM memory not based on final task success, but on minimizing epistemic uncertainty in intermediate summaries, significantly improving long-horizon agent performance.
The paper introduces Metacognitive Memory Policy Optimization (MMPO), a novel memory training approach that optimizes LLM memory not based on final task success, but on minimizing epistemic uncertainty in intermediate summaries, significantly improving long-horizon agent performance.
Papers
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
Ziyan Liu, Zhezheng Hao, Yeqiu Chen, Hong Wang +6 more
The paper introduces Metacognitive Memory Policy Optimization (MMPO), a novel memory training approach that optimizes LLM memory not based on final task success, but on minimizing epistemic uncertaint…