5 papers
Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking
Lijun Liu, Zhengzong Chen, Wenyan Li +2
Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly rely on a single reasoning traj…
MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards
Shihao Liu, Hao Yin, Lijun Liu +3
Tool learning enables large language models (LLMs) to use external tools for tasks beyond parametric knowledge. Reinforcement learning can optimize tool-call behavior from feedback…
Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents
Ruochen Zhou, Zhengyu Chen, Luan Zhang +3
Deep-research agents answer complex questions by interacting with search and browsing tools, yet they often search along a single evolving trajectory. Our trajectory-level analysis…
MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking
HONOR Agentic Search Team, Zhengzong Chen, Lei Tang +27
We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamenta…
PCTD: Preference-Guided Counterfactual Task Decomposition for Agent Tool Retrieval
Chu Zhao, Lei Tang, Minghang Li +5
Task decomposition aims to transform ambiguous instructions into executable atomic subtasks, thereby guiding high-precision tool retrieval. However, our analysis reveals that direc…