6 papers
To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning
Fengji Zhang, Tianyu Fan, Yuxiang Zheng +4
Recent advances in equipping Large Language Models (LLMs) with search tools and outcome-reward reinforcement learning (RL) have achieved new state-of-the-art results on open-domain…
DeepInnovator: Triggering the Innovative Capabilities of LLMs
Tianyu Fan, Fengji Zhang, Yuxiang Zheng +5
The application of Large Language Models (LLMs) in accelerating scientific discovery has garnered increasing attention, with a key focus on constructing research agents endowed wit…
R2ComSync: Improving Code-Comment Synchronization with In-Context Learning and Reranking
Zhen Yang, Hongyi Lin, Xiao Yu +5
Code-Comment Synchronization (CCS) aims to synchronize the comments with code changes in an automated fashion, thereby significantly reducing the workload of developers during soft…
ASearch: Ambiguity-Aware Question Answering with Reinforcement Learning
Fengji Zhang, Xinyao Niu, Chengyang Ying +7
Recent advances in Large Language Models (LLMs) and Reinforcement Learning (RL) have led to strong performance in open-domain question answering (QA). However, existing models stil…
Understanding DeepResearch via Reports
Tianyu Fan, Xinyao Niu, Yuxiang Zheng +5
DeepResearch agents represent a transformative AI paradigm, conducting expert-level research through sophisticated reasoning and multi-tool integration. However, evaluating these s…
HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks
Fengji Zhang, Linquan Wu, Huiyu Bai +6
Understanding and reasoning over diagrams is a fundamental aspect of human intelligence. While Large Multimodal Models (LMMs) have demonstrated impressive capabilities across vario…