AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

NeurIPSSpotlight2025

Authors
Ran Xu, Yuchen Zhuang, Zihan Dong, Ruiyu Wang, Yue Yu, Joyce C. Ho, Linjun Zhang, Haoyu Wang, Wenqi Shi, Carl Yang
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Search-augmented LLMs often struggle with complex reasoning tasks due to ineffective multi-hop retrieval and limited reasoning ability…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

reasoning retrieval llm

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive