Selected Publications

I develop scalable and reliable multi-agent foundation model systems for decision-making in complex multimodal real-world environments. My work is motivated by high-stakes domains such as science and healthcare. For a full publication list, please see my CV and Google Scholar.

Efficient Foundation Models

• [ICML 2026] EffGen: Enabling Small Language Models as Capable Autonomous Agents. Gaurav Srivastava, Aafiya Hussain, Chi Wang, Yingyan Celine Lin, and Xuan Wang.
• [ICLR 2026] BeyondBench: Benchmark-Free Evaluation of Reasoning in Language Models. Gaurav Srivastava, Aafiya Hussain, Zhenyu Bi, Swastik Roy, Priya Pitre, Meng Lu, Morteza Ziyadi, and Xuan Wang.
• [EMNLP 2025] ThinkSLM: Towards Reasoning in Small Language Models. Gaurav Srivastava, Shuxiang Cao, and Xuan Wang.
• [EMNLP 2025] DEBATE, TRAIN, EVOLVE: Self-Evolution of Language Model Reasoning. Gaurav Srivastava, Zhenyu Bi, Meng Lu, and Xuan Wang.

Multimodal Foundation Models

• [ICML 2026] BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models. Yi Fang, Haoran Xu, Jiaxin Han, Sirui Ding, Yizhi Wang, Yue Wang, and Xuan Wang.
• [CVPR 2026] Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs. Meng Lu, Ran Xu, Yi Fang, Wenxuan Zhang, Yue Yu, Gaurav Srivastava, Yuchen Zhuang, Mohamed Elhoseiny, Charles Fleming, Carl Yang, Zhengzhong Tu, Yang Xie, Guanghua Xiao, Hanrui Wang, Di Jin, Wenqi Shi, and Xuan Wang.
• [EMNLP 2025] BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration. Jun Hou, Le Wang, and Xuan Wang.

Agentic and Multi-Agent Systems

• [ICML 2026] A Diagnostic Study of Multi-Agent LLMs for Real-World Debates. Priya Pitre, Gaurav Srivastava, Lu Zhang, Le Wang, Naren Ramakrishnan, and Xuan Wang.
• [ACL 2025] ConsensAgent: Towards Efficient and Effective Consensus in Multi-Agent LLM Interactions Through Sycophancy Mitigation. Priya Pitre, Naren Ramakrishnan, and Xuan Wang.
• [ACL 2025] CrossAgentIE: Cross-Type and Cross-Task Multi-Agent LLM Collaboration for Zero-Shot Information Extraction. Meng Lu, Yuzhang Xie, Zhenyu Bi, Shuxiang Cao, and Xuan Wang.
• [EMNLP 2024] TriageAgent: Towards Better Multi-Agents Collaborations for Large Language Model-Based Clinical Triage. Meng Lu, Ho Brandon, Ren Dennis, and Xuan Wang.

Reliable and Trustworthy AI Systems

• [EMNLP 2025] A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare. Manar Aljohani, Jun Hou, Sindhura Kommu, and Xuan Wang.