5 papers
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…
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…
WebNavigator: Global Web Navigation via Interaction Graph Retrieval
Xuanwang Zhang, Yuteng Han, Jinnan Qi +3
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…
TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
Yidong Wang, Yunze Song, Tingyuan Zhu +11
The adoption of Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks. We identify two fundam…
RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios
Fei Zhao, Chengqiang Lu, Yufan Shen +9
While various multimodal multi-image evaluation datasets have been emerged, but these datasets are primarily based on English, and there has yet to be a Chinese multi-image dataset…