2 papers
cs.LG2026
Harness Policy Distillation: Aligning Agent Policies with Runtime Semantics
Junze Zhu, Weihao Chen, Zhiyang Zhou +2
Deploying a general-purpose model as an agent means running it inside a product-specific runtime harness that decides which actions are executable, how state advances, and when the…
cs.AI2026
Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems
Junze Zhu, Weihao Chen, Xuanwang Zhang +2
The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving capabilities, yet the centralized orchestration topology remains a critical po…