Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents
- Published
- Source
- arXiv
- Paper number
- 1112
- Field
- AI Agents
- arXiv ID
- 2609.28003
Key points
- Heterogeneous graph memory letting small LM tool agents learn from past failures
- Prevents recurrence of structural errors like missing observations and premature actions
- Improves long-horizon performance without large-model costs
- Directly applicable to ATF Works small-agent failure-learning loop design
Paper links
External research summaries. These are not HDATF publications or measured product results.