Perplexity's hint-guided self-distillation cuts its agent's tool-call failures by 21.2%

perplexity_ai · x · 2026-09-23

Perplexity published new research on post-training its Computer model to learn from its own errors using hint-guided self-distillation. In a live A/B test, a later checkpoint reduced tool-call failures by 21.2% relative to an earlier one.

Related event: Perplexity Open-Sources Hint-Guided Self-Distillation for Agent Training(3 posts)→

Original post →

More from coding & agent

coding & agent channel →