"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations

Researchers introduced CoLabScience, a proactive AI assistant that uses a reinforcement learning framework called PULI to autonomously intervene in biomedical research discussions. The system, trained on a new benchmark dataset BSDD, significantly outperformed existing methods in intervention precision and collaborative utility, demonstrating the potential of proactive LLMs in scientific discovery.

"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations https://aclanthology.org/2026.acl-long.1671.pdf Yang Wu /people/yang-wu-3505/ , Jinhong Yu /people/jinhong-yu/unverified/ , Jingwei Xiong /people/jingwei-xiong/ , Zhimin Tao /people/zhimin-tao/ , Xiaozhong Liu /people/xiaozhong-liu/ Abstract The integration of Large Language Models LLMs into scientific workflows presents exciting opportunities to accelerate biomedical discovery. However, the reactive nature of LLMs, which respond only when prompted, limits their effectiveness in collaborative settings that demand foresight and autonomous engagement. In this study, we introduce CoLabScience, a proactive LLM assistant designed to enhance biomedical collaboration between AI systems and human experts through timely, context-aware interventions. At the core of our method is PULI Positive-Unlabeled Learning-to-Intervene , a novel framework trained with a reinforcement learning objective to determine when and how to intervene in streaming scientific discussions, by leveraging the team’s project proposal and long- and short-term conversational memory. To support this work, we introduce BSDD Biomedical Streaming Dialogue Dataset , a new benchmark of simulated research discussion dialogues with intervention points derived from PubMed articles. Experimental results show that PULI significantly outperforms existing baselines in both intervention precision and collaborative task utility, highlighting the potential of proactive LLMs as intelligent scientific assistants.- Anthology ID: - 2026.acl-long.1671 - Volume: Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers /volumes/2026.acl-long/ - Month: - July - Year: - 2026 - Address: - San Diego, California, United States - Editors: Maria Liakata /people/maria-liakata/ , Viviane P. Moreira /people/viviane-p-moreira/unverified/ , Jiajun Zhang /people/jiajun-zhang/unverified/ , David Jurgens /people/david-jurgens/ - Venue: ACL /venues/acl/ - SIG: - Publisher: - Association for Computational Linguistics - Note: - Pages: - 36109–36129 - Language: - URL: https://aclanthology.org/2026.acl-long.1671/ https://aclanthology.org/2026.acl-long.1671/ - DOI: - Cite ACL : - Yang Wu, Jinhong Yu, Jingwei Xiong, Zhimin Tao, and Xiaozhong Liu. 2026. "Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations https://aclanthology.org/2026.acl-long.1671/ . In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers , pages 36109–36129, San Diego, California, United States. Association for Computational Linguistics. - Cite Informal : “Excuse me, may I say something…” CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations https://aclanthology.org/2026.acl-long.1671/ Wu et al., ACL 2026 - PDF: https://aclanthology.org/2026.acl-long.1671.pdf https://aclanthology.org/2026.acl-long.1671.pdf