ProtRLSearch: A Multi-Round Multimodal Protein Search Agent with Large Language Models Trained via Reinforcement Learning

2026-03-02

AI Summary

This work proposes the first protein search agent that supports multi-turn, multimodal interaction, addressing the limitations of existing approaches that are typically confined to single-round, text-only queries and struggle to integrate sequence information or exert fine-grained control over the search process—often leading to reasoning drift. By incorporating protein sequences as a multimodal input into large language model–driven search decisions and introducing a multidimensional reward mechanism, the agent enables reinforcement learning–based supervision over the entire search trajectory. Evaluated on ProtMCQs—a newly curated benchmark comprising 3,000 multiple-choice questions spanning varying difficulty levels—the method demonstrates significant improvements in reasoning accuracy and controllability on complex tasks involving protein function, phenotypic effects, and pathway networks.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Multiagent Learning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations

Abstract

Protein analysis tasks arising in healthcare settings often require accurate reasoning under protein sequence constraints, involving tasks such as functional interpretation of disease-related variants, protein-level analysis for clinical research, and similar scenarios. To address such tasks, search agents are introduced to search protein-related information, providing support for disease-related variant analysis and protein function reasoning in protein-centric inference. However, such search agents are mostly limited to single-round, text-only modality search, which prevents the protein sequence modality from being incorporated as a multimodal input into the search decision-making process. Meanwhile, their reliance on reinforcement learning (RL) supervision that focuses solely on the final answer results in a lack of search process constraints, making deviations in keyword selection and reasoning directions difficult to identify and correct in a timely manner. To address these limitations, we propose ProtRLSearch, a multi-round protein search agent trained with multi-dimensional reward based RL, which jointly leverages protein sequence and text as multimodal inputs during real-time search to produce high quality reports. To evaluate the ability of models to integrate protein sequence information and text-based multimodal inputs in realistic protein query settings, we construct ProtMCQs, a benchmark of 3,000 multiple choice questions (MCQs) organized into three difficulty levels. The benchmark evaluates protein query tasks that range from sequence constrained reasoning about protein function and phenotype changes to comprehensive protein reasoning that integrates multi-dimensional sequence features with signal pathways and regulatory networks.

Problem

• protein search
• multimodal input
• reinforcement learning
• search agent
• sequence-constrained reasoning

Innovation

• multimodal protein search
• reinforcement learning
• multi-round reasoning
• protein sequence integration
• search agent