paper-with-me

Papers

MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation

2026-03-04 · Lu Yang, Zelai Xu, Minyang Xie, Jiaxuan Gao, Zhao Shok, Yu Wang, Yi Wu arxiv

Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some flexibility, they fail to internalize the adaptive ability required for long-term improvement. Meta-Reinforcement Learning (meta-RL) provides an alternative by embedding the learning process directly within the model. However, existing meta-RL approaches for LLMs focus primarily on exploration in single-agent settings, neglecting the strategic exploitation necessary for multi-agent environments. We propose MAGE, a meta-RL framework that empowers LLM agents for strategic exploration and exploitation. MAGE utilizes a multi-episode training regime where interaction histories and reflections are integrated into the context window. By using the final episode reward as the objective, MAGE incentivizes the agent to refine its strategy based on past experiences. We further combine population-based training with an agent-specific advantage normalization technique to enrich agent diversity and ensure stable learning. Experiment results show that MAGE outperforms existing baselines in both exploration and exploitation tasks. Furthermore, MAGE exhibits strong generalization to unseen opponents, suggesting it has internalized the ability for strategic exploration and exploitation. Code is available at https://github.com/Lu-Yang666/MAGE.

📄 PDF Abstract BibTeX arXiv:2603.03680

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games

2025-05-23 · Shuhang Xu, Fangwei Zhong

Metaphors are a crucial way for humans to express complex or subtle ideas by comparing one concept to another, often from a different domain. However, many large language models (LLMs) struggle to interpret and apply met…

From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory

2025-11-11 · Siyu Xia, Zekun Xu, Jiajun Chai, Wentian Fan 외 arxiv

Large Language Models (LLMs) based agents have demonstrated remarkable potential in autonomous task-solving across complex, open-ended environments. A promising approach for improving the reasoning capabilities of LLM ag…

Reinforcement Learning

Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning

2021-08-30 · Shenao Zhang, Lei Han, Li Shen

In multi-agent reinforcement learning, the behaviors that agents learn in a single Markov Game (MG) are typically confined to the given agent number. Every single MG induced by varying the population may possess distinct…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

2023-10-29 · Zelai Xu, Chao Yu, Fei Fang, Yu Wang 외

Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of…

Decision MakingReinforcement Learning (RL)

ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning

2025-03-12 · Ziyu Wan, Yunxiang Li, Xiaoyu Wen, Yan Song 외

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning