GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning

2026-03-23 · Xiao Han, Yuzheng Fan, Sendong Zhao, Haochun Wang, Bing Qin arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.22096

Code (0)

등록된 구현이 없습니다.

EXG: Self-Evolving Agents with Experience Graphs

2026-05-18 · Yuxin Jin, Siyuan Zhang, Hanchen Wang, Lu Qin 외 arxiv

Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge …

Code Generation

Coordinating from Memory: Graph-Structured Experience Reuse for Multi-Agent Adaptation in Dynamic Manufacturing

2026-07-22 · Chengxiao Dai, Zhanhui Lin, Zhaokun Yan, Youyang Ni 외 arxiv

Dynamic manufacturing environments require multi-agent systems to coordinate effectively under frequent operational disturbances such as machine failures, urgent job arrivals, and processing time variations. Existing mul…

Multi-agent Reinforcement Learning Graph Neural Network

Metis: Bridging Text and Code Memory for Self-Evolving Agents

2026-06-23 · Zijie Dai, Siuhin He, Hui Li, Qihui Zhou 외 arxiv

Self-evolving agents improve over time by distilling experience from past executions and reusing it in future tasks. Existing systems represent such experience either as natural-language text injected into the agent cont…

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents

2026-04-09 · Xinshun Feng, Xinhao Song, Lijun Li, Gongshen Liu 외 arxiv

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are i…

Reinforcement Learning

Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents

2026-07-23 · Hu Gao, Yulong Chen, Lizhuang Ma arxiv

Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Existing agents typically formulate restoration as a tool-using process, …

Image Restoration