Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

• URL: http://arxiv.org/abs/2606.18216v1
• Date: Tue, 16 Jun 2026 17:46:02 GMT
• Title: Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
• Abstract summary: Zone of Proximal Policy Optimization (ZPPO) is inspired by Vygotsky's zone of proximal development.<n>ZPPO pairs one correct teacher response with one incorrect student response as anonymized candidates the student must discriminate.<n>A prompt replay buffer recirculates each hard question until it either graduates-the student's mean rollout accuracy on it reaches half- or is FIFO-evicted.
• Score: 89.89504265663057
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge distillation transfers a teacher's competence to a small student but is brittle in the small-student regime: forcing the student to imitate logits from a much larger teacher concentrates it on the teacher's sharpest modes, hurting generalization on benchmark families beyond the training corpus. Reinforcement learning (RL) avoids logit imitation by training on the student's own rollouts. However, on questions where every rollout fails-yielding zero advantage and being silently discarded-injecting a stronger teacher's response into the policy gradient breaks the on-policy assumption and induces drift. We introduce Zone of Proximal Policy Optimization (ZPPO), inspired by Vygotsky's zone of proximal development, which keeps the teacher inside the prompt rather than the policy gradient. On hard questions, ZPPO constructs two reformulated prompts: a Binary Candidate-included Question (BCQ) pairs one correct teacher response with one incorrect student response as anonymized candidates the student must discriminate, and a Negative Candidate-included Question (NCQ) aggregates the student's wrong rollouts into a single prompt to surface their shared failure modes. A prompt replay buffer recirculates each hard question until it either graduates-the student's mean rollout accuracy on it reaches half- or is FIFO-evicted under finite capacity, amplifying BCQ and NCQ inside the student's current zone of proximal development. On the Qwen3.5 family at four student scales (0.8B-9B) with a 27B teacher, post-trained as vision-language models and evaluated on a 31-benchmark suite (16 VLM, 10 LLM, 5 Video), ZPPO outperforms off/on-policy distillation and GRPO, with the largest gains at the smallest scale.

Related papers

• SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning [54.402550664505576]
  On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models to short-context students.<n>We study this setting by transferring proof-reasoning capabilities from the long-context reasoning model SU-01 to short-context student models.<n> Experiments on both same-family and different-family student models, including Qwen3, Qwen3.5, Intern-S2, GLM-4.7, Gemma-4, show consistent gains in mathematical reasoning.
  arXiv  Detail & Related papers  (2026-08-14T12:57:02Z)
• Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold [4.090731563364332]
  We argue that reinforcement learning policies should be viewed as local probes of a multi-basin reasoning solution manifold.<n>We propose an expand-then-compress framework that couples teacher construction with multi-teacher policy distillation.
  arXiv  Detail & Related papers  (2026-07-30T07:05:37Z)
• DemoPSD: Disagreement-Modulated Policy Self-Distillation [49.30809363804017]
  On-policy self-distillation has emerged as a practical method for training large language models.<n>DemoPSD steers the student toward a weighted geometric combination of the teacher and student distributions.
  arXiv  Detail & Related papers  (2026-07-02T17:58:29Z)
• On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents [50.78688247330029]
  On-Policy Distillation (OPD) is a natural recipe for transferring such capabilities to smaller students.<n>We propose Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout.<n>Guided-OPD improves Score by 21.1% and Success Rate by 25.5% over vanilla OPD on average.
  arXiv  Detail & Related papers  (2026-06-14T16:41:45Z)
• SocraticPO: Policy Optimization via Interactive Guidance [64.7524628699057]
  Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness.<n>We propose textbfSocraticPO (Socratic Policy Optimization), a policy-optimization framework that augments RL rollouts with Socratic-style natural-language guidance.
  arXiv  Detail & Related papers  (2026-06-03T09:08:29Z)
• Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation [49.117085054884676]
  On-policy distillation trains a student model on its own rollouts using dense feedback from a stronger teacher.<n>We operationalize this principle through a trajectory-specific release rule.<n> Experimental results across strong-to-weak distillation tasks indicate that this release rule consistently outperforms standard full-trajectory OPD.
  arXiv  Detail & Related papers  (2026-05-13T15:05:30Z)
• On-Policy Distillation with Best-of-N Teacher Rollout Selection [54.91780727674628]
  We propose BRTS, a Best-of-N Rollout Teacher Selection framework for on-policy distillation.<n>BRTS augments standard student-context OPD with a teacher-context supervision branch constructed from the teacher trajectory.<n>BRTS improves over standard OPD on challenging reasoning benchmarks, with the largest gains on harder datasets.
  arXiv  Detail & Related papers  (2026-05-10T19:49:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.