Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents

The paper introduces FRESH, a Failure-aware Retrieval framework that uses Experience-Structured Heterogeneous graphs to transform past successes and failures into structured external memory for tool‑using agents. By explicitly modeling dependencies among tasks, actions, errors, repairs, and execution conditions, FRESH enables frozen language models to reuse reliable strategies, avoid recurring failures, and make safer decisions in stateful tool interactions. Experiments on τ‑Bench and AppWorld with multiple open‑source models demonstrate that FRESH consistently improves task success and tool‑use reliability compared to no‑memory agents and other memory‑based baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms
• agents
• fine-tuning
• safety