arXiv Machine Learning August 4, 2026 By Yi Mao, Andrew Perrault

Training Small LLMs as Spatial Multi-Agent Policies

Read the original on arXiv Machine Learning →

arXiv:2608. 01425v1 Announce Type: cross Abstract: Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that such systems should be judged by their behavior, not only their reward.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 4

RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States

arXiv:2608. 02508v1 Announce Type: new Abstract: Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges.

By Yi Yang, Zhennan Chen, Yihong Zhuang, Tiehan Fan, Yinan Chen, Jian Li, Jian Yang, Ying Tai

llms agents reinforcement-learning

arXiv Machine Learning

Jul 15

When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary

arXiv:2607. 11953v1 Announce Type: new Abstract: Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut?

By Jim Allchin

agents reinforcement-learning

arXiv AI

Jun 29

Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs

arXiv:2606. 27909v1 Announce Type: cross Abstract: Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden side, so a model with strong language priors can score well without ever simulating opponents' incentives.

By Avni Mittal

llms agents

arXiv AI

Jul 7

Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning

arXiv:2607. 04470v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement learning (MARL), yet the training-time dynamics of this integration remain poorly understood.

By Faid Keddouri, Sohaib Houhou, Aissa Boulmerka, Nadir Farhi

llms agents reinforcement-learning

arXiv AI

6d ago

Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning

arXiv:2608. 11658v1 Announce Type: cross Abstract: Many reinforcement learning systems, from fleet management to traffic signal control, must serve an objective that changes dynamically after deployment, and retraining a policy for each new objective is prohibitively expensive.

By Zijian Zhao, Sen Li

agents reinforcement-learning safety

arXiv AI

Jul 9

RLVP: Penalize the Path, Reward the Outcome

arXiv:2607. 07435v1 Announce Type: cross Abstract: Agents acting on our behalf in the real world (e.

By Bojie Li, Noah Shi

agents reinforcement-learning

Related stories

RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States

When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary

Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs

Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning

Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning

RLVP: Penalize the Path, Reward the Outcome