MedCache: Efficient and Temporally Valid Memory for Longitudinal Clinical Agents
cs.LG, cs.DC, cs.MA
Submitted: 2026-08-30
Updated: 2026-08-30
License: http://creativecommons.org/licenses/by/4.0/
The gist: Longitudinal clinical agents must maintain an evolving patient state from evidence distributed across visits, time points, and specialties.
Terminology
Abstract
Longitudinal clinical agents must maintain an evolving patient state from evidence distributed across visits, time points, and specialties. However, how agent memory should be designed for this setting remains unclear. We introduce a benchmark of multi-visit, multi-specialty patient records that evaluates long-context evidence retrieval, cross-time evidence aggregation, and cross-specialty clinical reasoning. Using this benchmark, we systematically study four memory design choices: curation, organization, retrieval, and memory-augmented reasoning. We find that temporal validity is more important than simply retaining more history; specialty-factorized memory reduces context but can hide shared evidence; and multiple agents help when specialists must reason together, not merely when evidence comes from multiple memories. Guided by these findings, we propose MedCache, a hybrid framework that constructs temporally valid patient memory, organizes evidence into overlapping specialty views, routes each query to relevant memories, and adaptively invokes one or multiple specialists. Experiments show that MedCache improves reasoning accuracy and memory efficiency over strong single-agent and multi-agent baselines, while generalizing across model backbones and external datasets.
Sources
- LongHealth: A Question Answering Benchmark with Long Clinical Documents
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory
- MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
- MemGPT: Towards LLMs as Operating Systems
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
- MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks
- MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks