4 citations · 5 across the 9 of their papers we have counts for
4 papers · 1 filter
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…
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…
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
Yuhang Wu, Xiangqing Shen, Fanfan Wang +4
Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated…
WebNavigator: Global Web Navigation via Interaction Graph Retrieval
Xuanwang Zhang, Yuteng Han, Jinnan Qi +5
Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this limitation stems…