Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning

Ähnliche Einträge

• Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs
  von: Yang, Wei, et al.
  Veröffentlicht: (2025)
• TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models
  von: Bai, David, et al.
  Veröffentlicht: (2024)
• Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning
  von: Li, Dapeng, et al.
  Veröffentlicht: (2024)
• Evaluating Creativity and Deception in Large Language Models: A Simulation Framework for Multi-Agent Balderdash
  von: Hejabi, Parsa, et al.
  Veröffentlicht: (2024)
• Nucleolus Credit Assignment for Effective Coalitions in Multi-agent Reinforcement Learning
  von: Li, Yugu, et al.
  Veröffentlicht: (2025)