Paper
GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
Authors
Xiao Han, Yuzheng Fan, Sendong Zhao, Haochun Wang, Bing Qin
Abstract
Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit 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 organizes clinical experiences into a dual-layer memory graph, capturing both the decision structure within each experience and the relational dependencies across experiences, and supporting applicability-aware retrieval and online 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/xhan1022/gsem.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.22096v1</id>\n <title>GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning</title>\n <updated>2026-03-23T15:24:15Z</updated>\n <link href='https://arxiv.org/abs/2603.22096v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.22096v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit 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 organizes clinical experiences into a dual-layer memory graph, capturing both the decision structure within each experience and the relational dependencies across experiences, and supporting applicability-aware retrieval and online 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/xhan1022/gsem.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-23T15:24:15Z</published>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Xiao Han</name>\n </author>\n <author>\n <name>Yuzheng Fan</name>\n </author>\n <author>\n <name>Sendong Zhao</name>\n </author>\n <author>\n <name>Haochun Wang</name>\n </author>\n <author>\n <name>Bing Qin</name>\n </author>\n </entry>"
}