@inproceedings{xiao-etal-2026-gsem,
title = "{GSEM}: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning",
author = "Xiao, Han and
Fan, Yuzheng and
Zhao, Sendong and
Wang, Haochun and
Qin, Bing",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.507/",
pages = "11637--11660",
ISBN = "979-8-89176-459-0",
abstract = "Clinical decision-making agents can benefit from structured reuse of prior decision experience. Motivated by illness scripts, we study how to organize clinical experiences with explicit applicability conditions and inter-experience relations. However, many memory-augmented methods store experiences as independent records without conditional or relational structure, which may introduce noisy retrieval, unreliable reuse, and in some cases even hurt performance compared to direct LLM inference. We propose GSEM (Graph-based Self-Evolving Memory), a clinical memory framework that formalizes experiences as indications and contraindications and organizes them into a dual-layer memory graph. GSEM captures both intra-experience decision structure and inter-experience dependencies, supporting applicability-aware retrieval and feedback-driven calibration of node quality and edge weights. Across MedR-Bench and MedAgentsBench with two LLM backbones, GSEM achieves the highest average accuracy among all baselines, reaching 70.90{\%} and 69.24{\%} with DeepSeek-V3.2 and Qwen3.5-35B, respectively. Code is available at https://github.com/unname797/gsem."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2026-gsem">
<titleInfo>
<title>GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzheng</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sendong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haochun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Clinical decision-making agents can benefit from structured reuse of prior decision experience. Motivated by illness scripts, we study how to organize clinical experiences with explicit applicability conditions and inter-experience relations. However, many memory-augmented methods store experiences as independent records without conditional or relational structure, which may introduce noisy retrieval, unreliable reuse, and in some cases even hurt performance compared to direct LLM inference. We propose GSEM (Graph-based Self-Evolving Memory), a clinical memory framework that formalizes experiences as indications and contraindications and organizes them into a dual-layer memory graph. GSEM captures both intra-experience decision structure and inter-experience dependencies, supporting applicability-aware retrieval and feedback-driven calibration of node quality and edge weights. Across MedR-Bench and MedAgentsBench with two LLM backbones, GSEM achieves the highest average accuracy among all baselines, reaching 70.90% and 69.24% with DeepSeek-V3.2 and Qwen3.5-35B, respectively. Code is available at https://github.com/unname797/gsem.</abstract>
<identifier type="citekey">xiao-etal-2026-gsem</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.507/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>11637</start>
<end>11660</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
%A Xiao, Han
%A Fan, Yuzheng
%A Zhao, Sendong
%A Wang, Haochun
%A Qin, Bing
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F xiao-etal-2026-gsem
%X Clinical decision-making agents can benefit from structured reuse of prior decision experience. Motivated by illness scripts, we study how to organize clinical experiences with explicit applicability conditions and inter-experience relations. However, many memory-augmented methods store experiences as independent records without conditional or relational structure, which may introduce noisy retrieval, unreliable reuse, and in some cases even hurt performance compared to direct LLM inference. We propose GSEM (Graph-based Self-Evolving Memory), a clinical memory framework that formalizes experiences as indications and contraindications and organizes them into a dual-layer memory graph. GSEM captures both intra-experience decision structure and inter-experience dependencies, supporting applicability-aware retrieval and feedback-driven calibration of node quality and edge weights. Across MedR-Bench and MedAgentsBench with two LLM backbones, GSEM achieves the highest average accuracy among all baselines, reaching 70.90% and 69.24% with DeepSeek-V3.2 and Qwen3.5-35B, respectively. Code is available at https://github.com/unname797/gsem.
%U https://aclanthology.org/2026.emnlp-main.507/
%P 11637-11660
Markdown (Informal)
[GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning](https://aclanthology.org/2026.emnlp-main.507/) (Xiao et al., EMNLP 2026)
ACL