I am currently a Research Scientist / Staff Engineer at Qianfan (Baidu ACG), where I lead a strategy team and drive both research and engineering on LLMs and LLM-based Agents. Prior to joining Qianfan, I was a Research Scientist at Baidu Search from 2021 to 2024. I obtained my Ph.D. in 2021 from the Institute of Software, Chinese Academy of Sciences (ISCAS), advised by Prof. Le Sun and Prof. Xianpei Han. My research centers on Large Language Models, LLM-based Agents, Model Alignment, and related topics. I have authored more than 30 papers at top-tier AI venues such as ACL, NeurIPS, ICLR, and EMNLP, and was honored with the Outstanding Paper Award at EMNLP 2023.

🔔Recruitment🔔

We are seeking self-motivated Ph.D. candidates and graduates in (v)LLM, Agentic Reasoning, and Reinforcement Learning to join us as research interns and full-time researchers, respectively. Please send your CV to yanlingyong [at] baidu [dot] com if interested.

Recent Highlights

[2026-05] Our Deep Research System ranked #1 on the DeepResearch-Bench Leaderboard with overall score 58.03.
[2025-04] Launched the 心响 App as the Strategy Lead.

Recent Publications

Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin, Xiang Li. Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models. Accepted to ACL 2026 Findings.
Yucheng Shen, Jiulong Wu, Yikai Zhang, Lingyong Yan, Dawei Yin, Min Cao, Mang Ye. 2026. Beyond Action Units: Towards Multi-cue Facial Emotion Analysis. Pattern Recognition.
Yang Liu, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li, Lingyong Yan.LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts. Accepted to EACL 2026.
Jiulong Wu, Yucheng Shen, Lingyong Yan, Haixin Sun, Deguo Xia, Jizhou Huang, Min Cao. Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis. In AAAI 2026.
Yiqun Chen, Lingyong Yan, Weiwei Sun, Xinyu Ma, Yi Zhang, Shuaiqiang Wang, Dawei Yin, Yiming Yang, Jiaxin Mao. 2025. Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning. In NeurIPS 2025.
Zhengliang Shi, Lingyong Yan, Dawei Yin, Suzan Verberne, Maarten de Rijke, Zhaochun Ren. 2025. Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers. In NeurIPS 2025.
Junda Zhu*, Lingyong Yan*(co-first author), Shuaiqiang Wang, Dawei Yin, Lei Sha. 2025. Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking. In EMNLP 2025.
Jiulong Wu, Zhengliang Shi, Shuaiqiang Wang, Jizhou Huang, Dawei Yin, Lingyong Yan\(^\dagger\), Min Cao\(^\dagger\), Min Zhang. 2025. Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization. In EMNLP 2025.
Nuo Chen, Yufei Gao, Yongnan Jin, Yan Hu, Anningzhe Gao, Lingyong Yan, Benyou Wang. 2025. Mitigating Short Board Effect via Dynamic Reward Balancing in Multi-reward LLM Optimization. In EMNLP 2025 Findings.
Dongsheng Zhu, Weixian Shi, Zhengliang Shi, Zhaochun Ren, Shuaiqiang Wang, Lingyong Yan\(^\dagger\), Dawei Yin\(^\dagger\). 2025. Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation. In ACL 2025.
Zhengliang Shi, Yuhan Wang, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Dawei Yin, Zhaochun Ren. 2025. Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models. In ACL 2025 Findings.
Yukun Zhao, Lingyong Yan, Zhenyang Li, Shuaiqiang Wang, Zhumin Chen, Zhaochun Ren, Dawei Yin. 2025. Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model Generalization. In ACL 2025 Findings.
Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin and Ming Gao. 2025. PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization. In NAACL 2025.
Yougang Lyu, Lingyong Yan, Zihan Wang, Dawei Yin, Pengjie Ren, Maarten de Rijke and Zhaochun Ren. 2025. MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization. In ICLR 2025.
Zhengliang Shi, Shen Gao, Lingyong Yan, Yue Feng, Xiuyi Chen, Zhumin Chen, Dawei Yin, Suzan Verberne and Zhaochun Ren. 2025. Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents. In WWW 2025.

See all my publications here.

Services

Program Committee Member

Area Chair/Action Editor: ACL ARR
Reviewer: ACL, EMNLP, NAACL, AAAI, etc.

Journal Reviewer

Transactions on Knowledge and Data Engineering

Dr. Lingyong Yan