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

arXiv: https://arxiv.org/abs/2603.01464 · HTML: https://mlsanity.com/paper/2603.01464/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data](https://mlsanity.com/paper/2304.08247/) (2023)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding](https://mlsanity.com/paper/2206.02096/) (2022)
- [A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions](https://mlsanity.com/paper/2410.12837/) (2024)
- [MindSearch: Mimicking Human Minds Elicits Deep AI Searcher](https://mlsanity.com/paper/2407.20183/) (2024)
- [PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://mlsanity.com/paper/2501.10120/) (2025)
- [BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model](https://mlsanity.com/paper/2505.23579/) (2025)
- [ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training](https://mlsanity.com/paper/2403.07920/) (2024)
- [A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding](https://mlsanity.com/paper/2406.05540/) (2024)
- [Protein Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2502.17504/) (2025)
- [Rethinking Text-based Protein Understanding: Retrieval or LLM?](https://mlsanity.com/paper/2505.20354/) (2025)
- [BioMedSearch: A Multi-Source Biomedical Retrieval Framework Based on LLMs](https://mlsanity.com/paper/2510.13926/) (2025)
- [A PubMedBERT-based Classifier with Data Augmentation Strategy for Detecting Medication Mentions in Tweets](https://mlsanity.com/paper/2112.02998/) (2021)

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

- [Workflow Closure Is Not Scientific Closure in Auto-Research Systems](https://mlsanity.com/paper/2605.26200/) (2026)

## Abstract (arXiv)

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.