paper-with-me

Papers

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

2026-02-02 · Haozhen Zhang, Quanyu Long, Jianzhu Bao, Tao Feng, Weizhi Zhang, Haodong Yue, Wenya Wang arxiv

Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them rigid under diverse interaction patterns and inefficient on long histories. To this end, we present \textbf{MemSkill}, which reframes these operations as learnable and evolvable memory skills, structured and reusable routines for extracting, consolidating, and pruning information from interaction traces. Inspired by the design philosophy of agent skills, MemSkill employs a \emph{controller} that learns to select a small set of relevant skills, paired with an LLM-based \emph{executor} that produces skill-guided memories. Beyond learning skill selection, MemSkill introduces a \emph{designer} that periodically reviews hard cases where selected skills yield incorrect or incomplete memories, and evolves the skill set by proposing refinements and new skills. Together, MemSkill forms a closed-loop procedure that improves both the skill-selection policy and the skill set itself. Experiments on LoCoMo, LongMemEval, HotpotQA, and ALFWorld demonstrate that MemSkill improves task performance over strong baselines and generalizes well across settings. Further analyses shed light on how skills evolve, offering insights toward more adaptive, self-evolving memory management for LLM agents.

📄 PDF Abstract BibTeX arXiv:2602.02474

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents

2026-08-31 · Doyun Kim, Chanwoo Kim, Sugyeong Eo, Yeo-Chan Yoon 외 arxiv

LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution. Recent studies propose self-evolving agents that autonomously genera…

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

2026-04-02 · Hanrong Zhang, Shicheng Fan, Henry Peng Zou, Yankai Chen 외 arxiv

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bu…

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

2026-05-27 · Xujun Li, Kehan Zheng, Mingyuan Zhao, Yize Geng 외 arxiv

Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter u…

MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

2026-01-06 · Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou, Junwei Liao 외 arxiv

The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally e…

Reinforcement Learning

UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents

2026-02-05 · Han Xiao, Guozhi Wang, Hao Wang, Shilong Liu 외 arxiv

Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-hor…

Reinforcement Learning