arXiv AI
Belief-Conditioned Multi-Agent Actor Critic for Decentralized LLM Collaboration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 11
CCKS: Consensus-based Communication and Knowledge Sharing
arXiv:2606. 12281v1 Announce Type: cross Abstract: In Decentralized Training and Decentralized Execution (DTDE) for cooperative Multi-Agent Reinforcement Learning (MARL), action-advising-based knowledge sharing promotes interpretable and scalable cooperation among agents.
arXiv AI
Sep 10
MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games
The paper introduces MARBO, a framework that grounds large language model agents’ actions and speech in relational beliefs about hidden roles and team alignments in social deduction games. By providing preference feedback only when behaviors are supported by reliable relational beliefs and lead to favorable outcomes, MARBO encourages consistent learning under uncertainty. Experiments demonstrate that compact LLM agents using MARBO consistently outperform existing baselines in representative social deduction games.
arXiv AI
Oct 31
EpiAgent: Epistemic Self-Play for LLM Agents
EpiAgent introduces an explicit, learnable epistemic layer for large language model agents, enabling them to maintain and update beliefs about other agents’ private information. The framework splits the policy into Epistemic Update and Action Planning stages, optimized via a bi‑level Epistemic Self‑Play algorithm that rewards accurate belief predictions. Experiments in mixed and competitive settings show EpiAgent outperforms prompting and RL baselines, highlighting the benefits of dedicated epistemic training for belief inference and action planning.
arXiv AI
Oct 9
MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning
MA-JEPA is a stochastic world model designed for multi‑agent reinforcement learning that replaces observation reconstruction with joint‑embedding prediction. It uses a categorical latent state and a causal Transformer trained on posterior and action‑conditioned dynamics to generate imagined trajectories for actor‑critic learning. The model achieves strong performance on the SMAC benchmark, matching or surpassing the best reported mean win rates on half of the evaluated maps.
Hugging Face Trending Papers
Oct 13
Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards
Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates' contributions in...
Hugging Face Trending Papers
Aug 5
State2State: Environment-Derived Mid-Training for LLM Agents
Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers. Though effective, both remain bottlenecked by externally specified tasks and supervision signals, limiting the scalability and diversity of agent training.