Aravind Srinivas @AravSrinivas

We're sharing new research on our post‑training approach, which teaches the Perplexity Computer agent to learn from real user sessions by imitating good trajectories and explicitly correcting avoidable mistakes like bad tool calls (even when the overall trajectory was successful). The method combines rejection sampling fine‑tuning (RFT) with hint‑guided self‑distillation, and it cuts tool call failures by about 21% in live A/B tests [引用 @perplexity_ai]: New research: We post-trained a Computer model to learn from its own errors using hint-guided self-distillation. In a live A/B test, a later trained checkpoint reduced tool-call failures by 21.2% relative to an earlier checkpoint. https://t.co/3MFrp1yxDt