Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

📰 ArXiv cs.AI

arXiv:2605.30159v1 Announce Type: new Abstract: Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing approaches typically train these memory policies using outcome-based reinforcement learning, failing to localize where intermediate memory quality degrades. As interactions unfold, ambiguous recursive summaries progressively discard task-relevant information and introduce semantic noise. This exace

Published 29 May 2026

Full Article

Title: Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

Abstract:
arXiv:2605.30159v1 Announce Type: new Abstract: Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing approaches typically train these memory policies using outcome-based reinforcement learning, failing to localize where intermediate memory quality degrades. As interactions unfold, ambiguous recursive summaries progressively discard task-relevant information and introduce semantic noise. This exace
Read full paper → ← Back to Reads