Publications/Preprints

----2026----

MiroBench: Benchmarking Realism in Agentic Simulation of Real-world Discussions
Yaoning Yu, Ye Yu, Haojing Luo, Haohan Wang
[preprint | code]

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
Ye Yu, Xiaopeng Yuan, Haibo Jin, Heming Liu, Yaoning Yu, Haohan Wang
[preprint]

AgenticNet: Rethinking Multi-agent System Architectures with LLM-based Networks
Geyang Yu, Xiaopeng Yuan, Haibo Jin, Ye Yu, Yaoning Yu, Ke Chen, Haohan Wang

Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language Models
Ye Yu, Haibo Jin, Yaoning Yu, Jun Zhuang, Haohan Wang
European Chapter of the Association for Computational Linguistics (EACL) 2026 [pdf]

SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback
Yaoning Yu⁺, Ye Yu⁺, Peiyan Zhang, Kai Wei, Haojing Luo, Haohan Wang (⁺Equal contribution)
International Conference on Learning Representation (ICLR) 2026 [pdf]

Large Language Model-based Data Science Agent: A Survey
Chen Ke⁺, Peirang Wang⁺, Yaoning Yu⁺, Xianyang Zhan, Haohan Wang (⁺Equal contribution)
Transactions on Machine Learning Research (TMLR) 2026 [pdf]

----2025----

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Reasoning Models
Ye Yu, Yaoning Yu, Haibo Jin, Haohan Wang
NeurIPS 2025 Workshop on Efficient Reasoning Workshop [pdf]

Synthetic Data-Driven Prompt Tuning for Financial QA over Tables and Documents
Yaoning Yu, Kai-Min Chang, Ye Yu, Kai Wei, Haojing Luo, Haohan Wang
AI for Finance (AI4F) Workshop, The ACM International Conference on AI in Finance (ICAIF) 2025 [pdf]

More interesting papers coming, welcome to discuss and collaborate!🙂