# MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue

Source: [arXiv](https://arxiv.org/abs/2611.08433v1)  
Feed7 permalink: https://feed7.dev/p/2611-08433v1-0oq3wi7  
Published: 2026-11-05T18:27:20.000Z  
Trust: Needs Review (needs_review)

## Why Included

MedGraph organizes longitudinal dialogue as dated, person-attributed chains and retrieves them at the time a question asks about. The paper reports higher accuracy than five baselines on a medical dialogue benchmark.

## Source Summary

MedGraph stores dated, person-attributed medical facts and links medications, diagnoses, and measurements into chains. Retrieval ranks patient chains, selects the state relevant to the question's time, and adds original dialogue text; a patient profile supplies recorded safety facts.
For builders of agents with persistent memory, the design highlights three failure cases to guard against: outdated information, facts about the wrong person, and missing safety details. The paper reports **10.5 and 10.4 points** above the strongest baseline on MedMemoryBench with GPT and Qwen backbones, respectively.
These results are specific to longitudinal medical dialogue. The material does not establish performance in other domains or provide details about deployment with real patient data.

## Practical Implication

No separate implication recorded.

## Agent-Ready Context

MedGraph stores dated, person-attributed medical facts and links medications, diagnoses, and measurements into chains. Retrieval ranks patient chains, selects the state relevant to the question's time, and adds original dialogue text; a patient profile supplies recorded safety facts.
For builders of agents with persistent memory, the design highlights three failure cases to guard against: outdated information, facts about the wrong person, and missing safety details. The paper reports **10.5 and 10.4 points** above the strongest baseline on MedMemoryBench with GPT and Qwen backbones, respectively.
These results are specific to longitudinal medical dialogue. The material does not establish performance in other domains or provide details about deployment with real patient data.

## Connected Context

Feed7 judgment across 1020 accumulated Signals:

MedGraph adds a domain-tested design for persistent memory that preserves dates, people, relationships, and relevant dialogue when reconstructing state. It sharpens general source-linked memory patterns with explicit safeguards against stale, misattributed, or incomplete facts, though its reported gains apply to longitudinal medical dialogue.

- [nashsu/llm_wiki](https://feed7.dev/p/llm-wiki-1dqmknq) — Both use structured external memory for agent retrieval; MedGraph adds time- and person-aware state chains, while LLM Wiki emphasizes source-linked compiled knowledge and review.
- [Citation Needed: Provenance for LLM-Built Knowledge Graphs — Daniel Chalef, Zep AI](https://feed7.dev/p/citation-needed-provenance-for-llm-built-knowledge-graphs-daniel-chalef-1iob5t8) — MedGraph’s dated, attributed facts and dialogue links provide a concrete structure for provenance concerns raised by the talk about merged or changing facts in knowledge graphs.
- [How V7 gives AI agents institutional memory](https://feed7.dev/p/v7-1qw5ina) — Both present source-linked context as agent memory; MedGraph makes temporal and person attribution explicit, while V7’s summary leaves freshness and contradiction handling as open trust requirements.

## Context Map

- Layer: context
- Domains: research, data
- Topics: agent-memory, retrieval

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
