🛰️ Daily AI Frontier
‹ back to 2026-07-16

Experience Memory Graph: One-Shot Error Correction for Agents

Research Agents & Tool Use

Merged summary

TL;DR — Experience Memory Graph (EMG) is a framework for correcting LLM agent failures by reformulating recovery as a graph-matching problem, enabling one-shot error correction without costly test-time trial-and-error loops.

  • Converts failed and successful expert trajectories into directed action decision graphs, then extracts common subgraphs (successful workflows) and graph edit paths that specify corrective actions (add/delete/relabel) under given observations.
  • Stores insights in a memory graph with intra-task nodes and cross-task edges, enabling generalization across scenarios rather than brittle, task-specific prompt-based reflection.
  • At test time, retrieves relevant insights to guide the agent in a single, loop-free execution, avoiding the API/time costs of iterative reflection.
  • Reported to outperform state-of-the-art reflection baselines on ALFWorld and ScienceWorld in success rate and average reward, with no test-time trial-and-error (specific numbers not provided in the abstract).

Sources (1)

Experience Memory Graph: One-Shot Error Correction for Agents

arXiv cs.AI Wenjun Wang, Yuchen Fang, Fengrui Liu, Zibo Liang, Kai Zheng 2026-07-15 arXiv:2607.13884

TL;DR — Experience Memory Graph (EMG) is a framework for correcting LLM agent failures by reformulating recovery as a graph-matching problem, enabling one-shot error correction without costly test-time trial-and-error loops.

  • Converts failed and successful expert trajectories into directed action decision graphs, then extracts common subgraphs (successful workflows) and graph edit paths that specify corrective actions (add/delete/relabel) under given observations.
  • Stores insights in a memory graph with intra-task nodes and cross-task edges, enabling generalization across scenarios rather than brittle, task-specific prompt-based reflection.
  • At test time, retrieves relevant insights to guide the agent in a single, loop-free execution, avoiding the API/time costs of iterative reflection.
  • Reported to outperform state-of-the-art reflection baselines on ALFWorld and ScienceWorld in success rate and average reward, with no test-time trial-and-error (specific numbers not provided in the abstract).
item →