כתבה
arXiv cs.CL ·
CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents
CoMAP: פיתוח דגמי עולם ומדיניות סוכנים תוך-מסלולי לסוכני LLM. המאמר מציג פרקטיקה חדשה של Co-Evolving World Models and Agent Policies.
תקציר מקורי באנגליתarXiv:2606.02372v2 Announce Type: replace-cross Abstract: Equipping language agents with world models enables them to anticipate environment dynamics and evaluate candidate actions before execution. However, existing textual world models are typically fixed after training, preventing them from adapting to the on-policy state-action distributions induced by an evolving agent. Meanwhile, agent-improvement methods often rely on external rewards or verifiers, limiting their applicability in realistic interactive environments. In this paper, we propose COMAP, a novel framework that co-evolves textual world models and agent policies through closed-loop interaction. At each decision step, the world model predicts future state feedback for candidate actions, and the agent performs future-aware ref
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית