Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report RevisionBingsen Chen*, Boyan Li*, Ping Nie, Yuyu Zhang, Xi Ye, Chen Zhao ACL 2026 SAC Highlight Paper Code
Inter-Passage Verification for Multi-evidence Multi-answer QABingsen Chen, Shengjie Wang, Xi Ye, Chen Zhao ACL 2025 (Findings) Paper Code
Arithmetic Reasoning with LLM: Prolog Generation & PermutationXiaocheng Yang, Bingsen Chen, Yik-Cheung Tam NAACL 2024 Paper Code