Tag
This paper introduces Experience Memory Graph (EMG), a framework that reformulates agent failure recovery as a graph matching problem to enable one-shot error correction for LLM agents without test-time trial-and-error.
Introduces Diffusion Semi-Relaxed Fused Gromov-Wasserstein (DsrFGW), a novel method that integrates node features and structural connectivity for graph comparison via optimal transport and diffusion processes, demonstrating improved robustness to noise and missing edges on synthetic tasks.