Training AI agents on their failures with OPSD
A researcher involved in the ICML ’26 work says OPSD can turn records of agent failures into training feedback to help agents avoid repeating the same mistakes.
TLDR
OPSD stands for on-policy self-distillation. A researcher involved in the ICML ’26 work describes using failed agent traces as feedback to train agents to avoid the same mistakes. The researcher also credits the work with impact on Cursor’s Composer models, Applied Compute’s continual-learning platform and Perplexity Computer.
Combined views
113
1 Source, first seen ago
