Xiaoguang Li

QuRL: Rubrics As Judge For Open-Ended Question Answering

UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information Seeking

Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification

Distill Models by Aptitude: Efficient Reasoning Capability Distillation via Adaptive Data Curation and Overthinking Mitigation

DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning