cs.CLNov 10, 2026

BioMem: Agentic Memory for Biomedical LLM Agents

Authors: Mingchen Li, Yongkang Xiao, Rumeng Li, Rui Zhang, Hong Yu

Organizations: Manning College of Information and Computer Sciences, University of Massachusetts Amherst · VA Bedford Healthcare · Division of Computational Health Sciences, Department of Surgery, University of Minnesota · Department of Health Outcomes & Biomedical Informatics, University of Florida College of Medicine · 

Abstract

Large language models (LLMs) have demonstrated considerable potential in biomedical applications, while agentic memory systems have emerged as a promising approach to preserving and utilizing information across tasks and interactions. However, a fundamental question remains: how effectively and reliably do these systems retain, retrieve, update, and utilize biomedical information? In this study, we systematically investigate agentic memory in the biomedical domain, focusing on task effectiveness, retrieval quality, information fidelity, and long-term robustness. We evaluate five memory approaches across four LLMs in three representative settings: biomedical knowledge reasoning, clinical prediction, and long-term conversational memory. Our analyses reveal how memory construction, evidence relevance, and conversational history shape downstream biomedical performance, highlighting the distinct challenges of retrieving relevant information, preserving its fidelity, and effectively utilizing it for reasoning. Building on these findings, we introduce Hybrid Memory Retrieval and Utilization (HMRU), a training-free framework that jointly enhances evidence accessibility and task-aware utilization to improve biomedical reasoning and long-term conversational memory. HMRU achieves an average relative improvement of 8.6% across biomedical question-answering and conversational memory benchmarks, with additional gains in selected clinical prediction tasks. It further reduces conversational answer errors by 24.9% and closes 48.0% of the performance gap to full-context inference. Our findings provide a systematic characterization of biomedical agentic memory and practical insights into developing more effective and reliable memory-augmented LLM systems.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Human-Inspired Memory Architecture for LLM Agents

    May 8, 2026Doga Kerestecioglu, Alexei Robsky, Clemens Vasters +2Agent Memory ManagementLLM Agent Memory

  2. RaMem: Contextual Reinstatement for Long-term Agentic Memory

    Jun 22, 2026Wei Yang, Bryce Kan, Shixuan Li +5Agent MemoryLLM Agent Memory

  3. Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents

    Sep 13, 2026Yuanyi Song, Yukai Wang, Xinbei Ma +7LLM Agent MemoryLong-Term Conversational Memory