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

arXiv: https://arxiv.org/abs/2604.15588 · HTML: https://mlsanity.com/paper/2604.15588/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 68 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance](https://mlsanity.com/paper/2410.12361/) (2024)
- [OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples](https://mlsanity.com/paper/2307.11729/) (2023)
- [Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents](https://mlsanity.com/paper/2402.09205/) (2024)
- [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://mlsanity.com/paper/2406.12639/) (2024)
- [Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation](https://mlsanity.com/paper/2407.08940/) (2024)
- [SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions](https://mlsanity.com/paper/2412.04036/) (2024)
- [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://mlsanity.com/paper/2510.06186/) (2025)
- [ComPeer: A Generative Conversational Agent for Proactive Peer Support](https://mlsanity.com/paper/2407.18064/) (2024)
- [MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations](https://mlsanity.com/paper/2410.14204/) (2024)
- [Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning](https://mlsanity.com/paper/2502.07912/) (2025)
- [Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning](https://mlsanity.com/paper/2406.03600/) (2024)
- [I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation](https://mlsanity.com/paper/2407.14767/) (2024)
- [ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning](https://mlsanity.com/paper/2412.00631/) (2024)
- [ChatGPT Role-play Dataset: Analysis of User Motives and Model Naturalness](https://mlsanity.com/paper/2403.18121/) (2024)
- [Community-Based Hierarchical Positive-Unlabeled (PU) Model Fusion for Chronic Disease Prediction](https://mlsanity.com/paper/2309.03386/) (2023)
- [LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Design of Multi Active/Passive Core-Agent Architectures](https://mlsanity.com/paper/2409.11393/) (2024)
- [Intelligent Legal Assistant: An Interactive Clarification System for Legal Question Answering](https://mlsanity.com/paper/2502.07904/) (2025)
- [Large Language Model-based Role-Playing for Personalized Medical Jargon Extraction](https://mlsanity.com/paper/2408.05555/) (2024)
- [Toward Intelligent and Secure Cloud: Large Language Model Empowered Proactive Defense](https://mlsanity.com/paper/2412.21051/) (2024)
- [Y-Mol: A Multiscale Biomedical Knowledge-Guided Large Language Model for Drug Development](https://mlsanity.com/paper/2410.11550/) (2024)
- [Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs](https://mlsanity.com/paper/2511.15163/) (2025)

## Built on by (most cited first, 1 of 1)

- [BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation](https://mlsanity.com/paper/2609.10815/) (2026)

## Abstract (arXiv)

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.