Year: 2026
Type: conference-paper
Abstract: Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks.Yet existing approaches rely on external mechanisms that lack awareness of the agent's reasoning state, leading to suboptimal decisions.We propose Memory-as-Action (MemAct), a framework that treats working memory management as learnable policy actions.By formulating context management as in-place editing operations (deletion, insertion), MemAct enables joint optimization of information retention and task performance through end-to-end reinforcement learning.To address the computational challenges of dynamic context updates, we introduce Dynamic Context Policy Optimization, which restores training efficiency without compromising reasoning integrity.Experiments show that MemAct-RL-14B matches the accuracy of models 16× larger while reducing average context length by 51%, with learned strategies that adapt to model capabilities and generalize across task complexities.The code and datasets are available at https://github.com/ADaM-BJTU/MemAct.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4415270781