AI RESEARCH
Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
arXiv CS.LG
•
ArXi:2605.02168v1 Announce Type: cross Language model (LM)-based agents have nstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-horizon planning and reasoning. To address this, we propose an enhanced multi-agent framework that decomposes automation into three roles: a planner for high-level decision-making, an actor for task execution, and a memory manager for contextual reasoning.