# Perplexity — A good teacher meets the student where they are

- Company: Perplexity (perplexity.ai)
- Announced: 2026-10-21
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.perplexity.ai/hub/blog/a-good-teacher-meets-the-student-where-they-are
- Record: https://forck.live/items/26910-a-good-teacher-meets-the-student-where-they-are
- Subject: Perplexity

Perplexity researchers propose JOLT, a method that trains one model in two roles so a stronger teacher gives guidance matched to the student's current ability. Outcome-reward reinforcement learning gives a sparse signal that cannot tell which intermediate actions helped or hurt, which limits sample efficiency on long-horizon agentic tasks where successes are rare. On-Policy Distillation adds denser token-by-token feedback from a stronger teacher, but a model good at a task is not necessarily good at teaching it, since its feedback may sit beyond the student's reach. Building on On-Policy Self-Distillation, JOLT uses a single model as a teacher with privileged information such as verified solutions and as a student without it, training both jointly. The student follows the standard distillation objective, while the teacher's updates push its feedback to move the student in the same direction as RL on the student's own reward. The researchers call a teacher reward-consistent when the distillation update it induces matches the student's expected-reward policy gradient up to positive scaling, and define a teacher that satisfies this condition. JOLT+ further adds outcome rewards to the student's distillation signal, and the experiments report gains in both model performance and training efficiency across mathematical reasoning, coding, and agentic tasks.

## Evidence

Verbatim from https://www.perplexity.ai/hub/blog/a-good-teacher-meets-the-student-where-they-are:

> We train the two roles jointly. The student follows the standard distillation objective. The teacher’s objective pushes its feedback to move the student in the same direction as RL on the student's own reward. Together, these objectives train the teacher to meet the student where they are and help the student learn from guidance within their reach.

---

Record: https://forck.live/items/26910-a-good-teacher-meets-the-student-where-they-are
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md