mlsanityData to 14 Oct 2026

Personalized State-Transition-Aware Memory for Clinical Agents

arXiv 2609.38490 ↗First posted 29 Sep 2026cs.CL cs.AIcited by 0

On the map: LLM agents and tool use → Medical and scientific domain agents also fits: Agent memory systems

Abstract (arXiv)

Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to understand them. Simply accumulating memories leaves it unclear which information still applies, whereas overwriting earlier memories can erase evidence needed to reconstruct treatment history and clinical trajectories. We introduce STAM, a state-transition-aware memory framework that records state changes as new clinical entries arrive. STAM combines semantic retrieval with typed clinical relations to identify affected memories, maintaining current information in Active and superseded or resolved information in History. At read time, a query-dependent gate selectively serves historical memory. Across four longitudinal clinical benchmarks, we evaluate STAM with downstream question answering, direct state-maintenance diagnostics, and comparisons at approximately matched context lengths.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 27 of its 30 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

27 of 30 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived Dialogues1 Sep
  2. 2026LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making10 Jul

Other references · 25

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  4. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  5. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
  6. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  7. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  8. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 400
  9. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 237
  10. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 180
  11. 2025MemOS: A Memory OS for AI Systemcited by 138
  12. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 129
13 more
  1. 2026STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?cited by 50
  2. 2026From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agentscited by 36
  3. 2025TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Recordscited by 34
  4. 2026APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AIcited by 17
  5. 2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agentscited by 14
  6. 2026Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledgecited by 14
  7. 2026TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memorycited by 8
  8. 2026Can Agent Memory Systems Track Evolving State?cited by 7
  9. 2026A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memorycited by 4
  10. 2026MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Modelscited by 4
  11. 2026ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IVcited by 2
  12. 2026MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcarecited by 2
  13. 2026MedCache: Efficient and Temporally Valid Memory for Longitudinal Clinical Agentscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture
  2. 2026Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes
  3. 2026PatientWM: Towards Generalizable Clinical World Models via Unified Patient States
  4. 2026GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
  5. 2026MSM-Mem: A Universal Medical Structured Multimodal Memory Framework for Medical AI Agents
  6. 2025GraphMed-LT: Patient-Specific Graph Memory with Latent Clinical Thought Refinement for Multi-Turn Medical Conversations
  7. 2025Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction
  8. 2026GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR Events