Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Lu, Xu, Zelai, Xie, Minyang, Gao, Jiaxuan, Shok, Zhao, Wang, Yu, Wu, Yi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game
di: Xu, Zelai, et al.
Pubblicazione: (2023)

Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
di: Xu, Zelai, et al.
Pubblicazione: (2025)

VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
di: Xu, Zelai, et al.
Pubblicazione: (2025)

In-context Exploration-Exploitation for Reinforcement Learning
di: Dai, Zhenwen, et al.
Pubblicazione: (2024)

Exploration and Exploitation Errors Are Measurable for Language Model Agents
di: Park, Jaden, et al.
Pubblicazione: (2026)

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn
di: Yu, Chao, et al.
Pubblicazione: (2025)

Verifiable Process Rewards for Agentic Reasoning
di: Yuan, Huining, et al.
Pubblicazione: (2026)

MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
di: Yuan, Huining, et al.
Pubblicazione: (2025)

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
di: Gao, Jiaxuan, et al.
Pubblicazione: (2025)

ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism
di: Liu, Jia, et al.
Pubblicazione: (2025)

WESE: Weak Exploration to Strong Exploitation for LLM Agents
di: Huang, Xu, et al.
Pubblicazione: (2024)

Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
di: Zhang, Shilin, et al.
Pubblicazione: (2025)

MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
di: Yang, Ruiyi, et al.
Pubblicazione: (2026)

LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination
di: Liu, Jijia, et al.
Pubblicazione: (2023)

Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning
di: Zhang, Ruize, et al.
Pubblicazione: (2025)

First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
di: Norman, Ben, et al.
Pubblicazione: (2023)

OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
di: Yang, Yiqin, et al.
Pubblicazione: (2026)

Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
di: He, Yidong, et al.
Pubblicazione: (2026)

Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent
di: Hoppmann, Björn, et al.
Pubblicazione: (2026)

Quantum-Inspired Multi Agent Reinforcement Learning for Exploration Exploitation Optimization in UAV-Assisted 6G Network Deployment
di: Taghavi, Mazyar, et al.
Pubblicazione: (2025)

MAGE-KT: Multi-Agent Graph-Enhanced Knowledge Tracing with Subgraph Retrieval and Asymmetric Fusion
di: Yu, Chi, et al.
Pubblicazione: (2026)

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
di: Liang, Kun, et al.
Pubblicazione: (2026)

Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust
di: Lei, Shijun, et al.
Pubblicazione: (2026)

WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
di: Xu, Zelai, et al.
Pubblicazione: (2026)

A Survey on Self-play Methods in Reinforcement Learning
di: Zhang, Ruize, et al.
Pubblicazione: (2024)

MAGE:A Multi-stage Avatar Generator with Sparse Observations
di: Du, Fangyu, et al.
Pubblicazione: (2025)

Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning
di: Ma, Zeyuan, et al.
Pubblicazione: (2024)

Meta-RL Induces Exploration in Language Agents
di: Jiang, Yulun, et al.
Pubblicazione: (2025)

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning
di: Zhang, Yaolun, et al.
Pubblicazione: (2026)

MetaDE: Evolving Differential Evolution by Differential Evolution
di: Chen, Minyang, et al.
Pubblicazione: (2025)

Query Decomposition for RAG: Balancing Exploration-Exploitation
di: Petcu, Roxana, et al.
Pubblicazione: (2025)

MAXS: Meta-Adaptive Exploration with LLM Agents
di: Zhang, Jian, et al.
Pubblicazione: (2026)

Towards Strategic Persuasion with Language Models
di: Cheng, Zirui, et al.
Pubblicazione: (2025)

PACE: A Pragmatic Agent for Enhancing Communication Efficiency Using Large Language Models
di: Li, Jiaxuan, et al.
Pubblicazione: (2024)

Disentangling Exploration of Large Language Models by Optimal Exploitation
di: Grams, Tim, et al.
Pubblicazione: (2025)

Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation
di: Zhang, Weiming, et al.
Pubblicazione: (2026)

WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration
di: Zhang, Yao, et al.
Pubblicazione: (2024)

VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play
di: Xu, Zelai, et al.
Pubblicazione: (2025)

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
di: Huang, Lei, et al.
Pubblicazione: (2026)

Exploitation Is All You Need... for Exploration
di: Rentschler, Micah, et al.
Pubblicazione: (2025)