cs.CLNov 5, 2026
SaveMedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue
Organizations: University of Michigan · Georgetown University · Johns Hopkins University · Harvard University
Abstract
LLM-based medical assistants that follow a patient across visits need a memory that keeps the patient's clinical state correct as it changes. We examine the errors of five memory systems on longitudinal medical dialogue and find three recurring causes: the retrieved evidence gives an outdated state, includes another person's health facts, or lacks a safety fact the answer depends on. We present MedGraph, a graph memory built for these three cases. Construction extracts dated facts from each session, attributes each fact to the person it describes, and links medication, diagnosis, and measurement records into chains that keep earlier states. Retrieval ranks the patient's chains as units, reads each chain at the time the question asks about, and adds the original dialogue text; a patient profile lists every recorded safety fact with every question. On MedMemoryBench, MedGraph has the highest overall accuracy with both a GPT and a Qwen backbone, 10.5 and 10.4 points above the strongest of five baselines, with efficient memory construction and answering in the GPT setting.
Figures & tables
Figure 1: Three challenges in longitudinal medical memory. (a) We inspect 150 wrong answers from five memory systems, 30 per system, and the evidence supplied to the answering model. Each square represents one wrong answer, with colors indicating the observed challenges. Split squares indicate two challenges; gray squares indicate failures outside these categories. Categories overlap, so their counts do not sum to 150. (b) LightMem misses the patient’s September 10 walking-distance measurement, leading to an answer based on an older reading. (c) MemOS retrieves the father’s medication when the patient asks about their own symptoms. (d) REMem omits a recorded co-trimoxazole allergy when answering a later question about antibiotics.
Figure 2: MedGraph overview. (a) Construction: clinical facts are extracted from each session and linked to the person they describe in the fact graph (L2). Medication, condition, lab, and vital facts form chains by entity, subject, and type, following insertion order, with the patient’s and other people’s facts kept separate. (b) Retrieval: the system ranks the patient’s records, treating each chain as one unit and each fact outside a chain as an individual unit. For selected chains, it includes the matched fact, the state at the requested time, and the preceding record. It also adds causally linked facts, records from any explicitly requested date window, and original dialogue excerpts. The answer model receives the question, the assembled evidence, and the patient profile (L3), then generates an answer in one LLM call.
| Fact type | Storage | Current record |
|---|---|---|
| medication, condition | chain, insertion order | chain tail |
| lab, vital | chain, all kept | latest by date |
| symptom, event | individual records | – |
| safety | append-only | all in profile |
| preference | individual records | – |
Table 1: Storage and update policy by fact type.
| Avg. | EEM | MQ | TLA | SUA | IG | MCD | |
| GPT backbone | |||||||
| Emb. RAG | 41.4 | 50.5 | 69.8 | 46.3 | 42.0 | 22.2 | 17.2 |
| Mem0 | 40.3 | 47.5 | 65.3 | 36.2 | 63.0 | 20.2 | 9.7 |
| MemOS | 39.1 | 46.0 | 61.8 | 50.3 | 61.0 | 13.6 | 2.2 |
| LightMem | 37.1 | 40.0 | 68.3 | 44.6 | 53.0 | 13.6 | 3.2 |
| REMem | 23.0 | 27.5 | 53.8 | 23.2 | 28.0 | 3.5 | 2.2 |
Table 2: Accuracy (%) with GPT ( gpt-6-luna builds memory, gpt-5.1 answers) and Qwen (Qwen3-30B-A3B-Instruct-2507 does both); claude-sonnet-4-5 judges. Avg. is the mean across six types. Dark/light blue: best/second best among six methods; best scores are also bold. Indented BM25 controls (Section 6.1 ): BM25 only changes only MedGraph’s ranking; built facts, BM25 retrieves extracted facts without chain retrieval, the profile, or source windows; raw text, BM25 builds no memory and retrieves whole sessions with the benchmark’s BM25 implementation.
Figure 3: Accuracy as histories grow (GPT). (a) Avg. after every ten patient sessions, using new questions. (b) The same 105 early EEM and TLA questions at their original checkpoints and after the full history, with unchanged reference answers. LightMem uses one rebuilt memory for both measurements (Appendix E ).
| State | Subject | Safety | ||||
| Avg. | Acc. | Polluted entries | Polluted questions | Missing | Acc. | |
| Emb. RAG | 41.4 | 49.0 | 12.2 | 22.8 | 38.2 | 44.0 |
| Mem0 | 40.3 | 55.4 | 22.4 | 55.6 | 51.7 | 44.9 |
| MemOS | 39.1 | 53.4 | 17.1 | 40.4 | 59.6 | 39.7 |
| LightMem | 37.1 | 52.9 | 21.8 | 74.1 | 74.2 | 40.8 |
| REMem | 23.0 | 35.8 | 27.3 | 63.6 | 80.9 | 25.6 |
Table 3: The three challenges (%, GPT). State: accuracy on 204 changed-state questions (Appendix D ). Subject: percentages of evidence entries about other people and questions with such evidence (lower is better; Appendix D ). Safety: the missing-fact rate on 89 questions with identified required safety facts, and mean MQ and IG accuracy on 180 safety-dependent questions. Avg. follows Table 2 . Bold: best among six systems. Bottom rows omit one component.
| Question (patient 4, IG): “Doctor, my knee pain is back. Can I take a painkiller again?” | ||
|---|---|---|
| Gold : Avoid ibuprofen, which the doctor stopped; with perindopril and spironolactone it risks kidney damage and high potassium. | ||
| Evidence | Answer | |
| LightMem ✗ | “Took ibuprofen 200 mg as needed for about a year” (Jan 3) and “the doctor told the patient to stop ibuprofen” (Jan 5), with no mark of which is current; none names perindopril or spironolactone. | “If the pain is very bad, a one-off 200 mg of ibuprofen is acceptable.” |
| MemOS ✗ | Knee-pain and exercise memories. Its memory holds the order to stop ibuprofen and the interaction warning, but neither is retrieved. | No drug record; an old painkiller “can be considered”. |
| REMem ✗ | General advice and another person’s records, e.g., “continue mecobalamin to support nerve recovery” . Its stored interaction warning is not retrieved. | Asks whether the user is “Xiao Zhou, who used celecoxib”. |
| MedGraph ✓ | Current medications: perindopril, spironolactone, and valsartan, all “in use” with dates. Safety: “[interaction] ibuprofen: with perindopril and spironolactone, adds kidney and potassium risk; do not keep taking it” (2024-01-03). | “With perindopril, valsartan, and spironolactone, do not take ibuprofen on your own.” |
Table 4: A question that needs the current state and a safety fact (translated and shortened). Red: misleading; blue: what the correct answer needs. More examples are in Appendix F .
Figure 4: Storage and indexing issues in sampled failures. Percentages use 31, 31, 32, 31, 38, and 25 retained cases in the plotted order. Numbers inside bars are counts. LightMem uses a rebuilt memory (Appendix E ).
Figure 5: Accuracy against cost (GPT backbone): (a, b) LLM calls and input tokens spent constructing memory; (c) seconds per question, the wall-clock time from the question to the answer string, including the method’s retrieval and the reader’s generation and excluding judging. The top right is best; dashed lines mark the Pareto frontier.
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
| Method | Builder | Evidence per question |
|---|---|---|
| Embedding RAG | none | top 5 chunks ( 4,096 tok.) |
| Mem0 | gpt-6-luna | top 5 memories |
| MemOS | gpt-6-luna | top 5 memories |
| LightMem | gpt-6-luna | top 20 memories |
| REMem | gpt-6-luna | top 5, gist agent |
| MedGraph | gpt-6-luna | 8 units, 4 causal, dates |
Table 5: Baseline settings. The reader ( gpt-5.1 ), answer prompt, judge ( claude-sonnet-4-5 ), and embedder (bge-small-zh-v1.5) are shared by all methods.
| Question (patient 9, inference): “Doctor, I am always tired in the afternoon. Is it the medicine? Should I stop it for now?” | |
| Gold : do not stop; the afternoon fatigue was there before the diabetes drugs were started, so it is unlikely to be their side effect. | |
| Embedding RAG, MemOS ✗ | MedGraph ✓ |
| Evidence. Embedding RAG retrieves three noise sessions—two general health consultations and one about the father’s blood-pressure drugs —and none of the patient’s own. Three of MemOS’s five memories are about the father’s blood pressure, e.g., “if the father’s systolic pressure falls to about 110 mmHg with dizziness, indapamide can be paused for a day” . | Evidence. Profile: “DPP-4 inhibitor: active, started 2024-01-10” ; “metformin: active, 1,500 mg/day on a new regimen for about two weeks” (both as of 2024-01-10). Matched facts: “(2024-01-04) afternoon fatigue, like being drained, worst at 3–4 pm” ; “(2024-01-08) afternoon fatigue and poor concentration”; “(2024-01-10) afternoon fatigue still present”. No fact about the father appears. |
| Answer (both discuss the father’s drugs). “…not likely caused by your father’s current drugs (valsartan/amlodipine) …” (Embedding RAG). | Answer. The fatigue was reported before the drug change, so it is unlikely to be a side effect; do not stop on your own. |
| Why. The subject filter keeps the father’s sessions out and the profile gives the patient’s own diabetes drugs, so the answer is about the right person’s drugs. The dated fatigue records in the evidence start on 2024-01-04, before the DPP-4 inhibitor is recorded as added (2024-01-10). Mem0, LightMem, and REMem also answer wrongly; we show the two baselines whose evidence is about the father. | |
Table 6: Example A (whose fact).
More in this topic
Long-Term Conversational Memory
Long-term conversational memory helps AI assistants retain, update, and use information from past conversations across sessions.
See all 274 papers