arXiv AI
A Generalist Hanabi Agent
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 6
The Yokai Learning Environment: Tracking Beliefs Over Space and Time
arXiv:2508. 12480v3 Announce Type: replace Abstract: The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm by measuring the performance of independently trained agents when paired.
arXiv AI
Jun 2
MARFT: Multi-Agent Reinforcement Fine-Tuning
arXiv:2504. 16129v5 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based Multi-Agent Systems (LaMAS) have demonstrated strong capabilities on complex agentic tasks requiring multifaceted reasoning and collaboration, from high-quality presentation generation to scientific research.
arXiv Machine Learning
Jul 23
Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning
arXiv:2607. 19809v1 Announce Type: cross Abstract: In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability.
arXiv AI
Aug 10
IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents
arXiv:2608. 06735v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution.
arXiv Machine Learning
Oct 7
Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models
The paper introduces CASTLE, a framework for fully decentralized multi‑agent reinforcement learning that uses two offline‑trained world models to provide in‑context guidance to independent agents. A Local Dynamics World Model captures each agent’s trajectory dynamics, while a Semantic‑Social World Model predicts short‑horizon task and social outcomes for candidate actions based on counterfactual simulator rollouts. During online learning, these frozen models supply prediction logits to an independent PPO policy, enabling agents to compare potential actions prospectively rather than relying solely on scalar rewards. CASTLE outperforms existing baselines on several multi‑particle benchmark tasks, achieving the highest mean final scores across 30 seeds.
arXiv Machine Learning
Sep 4
LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games
The paper explores a runtime strategy-selection framework where a large language model (LLM) guides a pre‑trained reinforcement learning (RL) policy for non‑player characters (NPCs) in a Unity combat game without altering the underlying policy. Five NPC agents sharing a PPO policy were compared in a baseline setup and an LLM‑augmented setup, where a locally hosted Mistral 7B model assigns one of four tactical tags every five seconds based on live game state. Across 600 episodes against three scripted opponents, the LLM‑augmented agents more than doubled their win rate against a Balanced opponent, improved performance against an Evasive opponent, but struggled against an Aggressive opponent due to over‑reliance on encirclement; analysis of 2,430 strategy selections revealed limited zero‑shot differentiation with the model favoring Surround in 83.8% of cases.