MARS: Reinforcing Multi-Agent Reasoning of LLMs through Self-Play in Strategic Games
Paper
•
2510.15414
•
Published
•
1
MARSHAL
MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
Note Note: This paper has been updated to v2 on arXiv. MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
-
nics-efc/MARSHAL-Generalist-Qwen3-4B
Text Generation • 4B • Updated • 39 -
nics-efc/MARSHAL-Generalist-Qwen3-8B
Text Generation • 8B • Updated • 30 -
nics-efc/MARSHAL-Tic-Tac-Toe-Qwen3-4B
Text Generation • 4B • Updated • 35 -
nics-efc/MARSHAL-Kuhn-Poker-Qwen3-4B
Text Generation • 4B • Updated • 31 -
nics-efc/MARSHAL-Mini-Hanabi-Qwen3-4B
Text Generation • 4B • Updated • 29