> ## Content Index
> Fetch the complete content index at: https://www.ai-360.online/llms.txt
> Use this file to discover other available public pages before exploring further.

# Perplexity and NVIDIA publish JOLT self-distillation method
- URL: https://www.ai-360.online/perplexity-a-good-teacher-meets-the-student-where-they-are/
- Published: 2026-10-21T12:00:00.000Z
- Updated: 2026-10-31T20:33:15.000Z
- Description: Perplexity and NVIDIA researchers have published JOLT, which trains teacher and student models together and reports gains over GRPO on reasoning tests.
- Author: Nicholas Lipinski
- Tags: 1. Enterprise AI, News, #company-perplexity, #company-nvidia

[Perplexity](https://www.perplexity.ai/?ref=ai-360.online) and [NVIDIA](https://www.ai-360.online/nvidia/) researchers have published JOLT, a training method that jointly trains a teacher and a student model to improve reasoning and agentic performance, [Perplexity said on 21 October 2026](https://www.perplexity.ai/hub/blog/a-good-teacher-meets-the-student-where-they-are?ref=ai-360.online).

The work targets a weakness of reinforcement learning in post-training: a single outcome reward gives a sparse signal that does not show which intermediate steps helped. A common fix, on-policy distillation, uses a stronger teacher to give token-by-token feedback.

The researchers argue that privileged information can make a teacher better at solving a task without making it better at teaching. JOLT therefore trains the teacher relative to the student's current behaviour.

With student outcome rewards, the JOLT+ variant reported absolute gains over GRPO of 1.5 percentage points on GSM8K, 4.2 on MATH, 3.0 on LCBv6, 9.9 on AppWorld and 2.7 on Terminal-Bench 2.1 pass@1\. On MATH, JOLT used 13 times fewer completion tokens and 6.5 times fewer processed training tokens than GRPO at matched accuracy.

"We will open-source the code soon," the authors wrote.

The results are the authors' own and had not been independently replicated at publication.

---