Skip to content

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Sep 2026 · 0 citations · 50 references
Computer Science

TL;DR

Across four base/RL-teacher pairs spanning different scales, architectures, and pre-training lineages, RIDE approaches or exceeds the RL-trained teacher on every pair and is the only method whose mean does so, and it consistently outperforms output-space extrapolation, which degrades the student whenever the teacher is close to its base.

Abstract

On-policy distillation (OPD) trains a student to match the teacher's next-token distributions on the student's own trajectories and has yielded substantial empirical gains. Generalized variants allow the student to surpass the teacher by extrapolating an implicit reward in output space. The language-model head, however, attenuates this change anisotropically: much of the change encoded in the teacher's hidden states reaches the logits at a small fraction of its weight, and the sampled-token log-probability ratios on which output-space extrapolation relies inject noise that the extrapolation amplifies, making training unstable. We observe that reinforcement learning (RL) shifts a model's internal representations relative to its base checkpoint, and that the direction of this shift can be measured at every layer. Motivated by this observation, we propose RIDE (RL-Induced Direction Extrapolation), which extrapolates the RL-induced change directly in representation space: at every layer and token position, RIDE computes the residual between the teacher and its pre-RL checkpoint and regresses the student's hidden states toward targets displaced beyond the teacher along this residual. Conditioned on a sampled trajectory, this regression is equivalent to maximizing a linear directional reward defined by the residual under a quadratic penalty centered at the teacher, which makes explicit how the objective moves the student along the RL-induced direction while limiting its deviation from the teacher. Across four base/RL-teacher pairs spanning different scales, architectures, and pre-training lineages, RIDE approaches or exceeds the RL-trained teacher on every pair and is the only method whose mean does so, and it consistently outperforms output-space extrapolation, which degrades the student whenever the teacher is close to its base. Project page: https://github.com/xixixixixxxx/RIDE.

View source

Similar papers

Preprint Sep 2026

What Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation

Trajectory Dropout provides a simple mechanism for strengthening token-level supervision across model scales and OPD objectives and consistently improves average performance across teacher--student model pairs of different scales and six mathematical reasoning benchmarks.

Zi-Zhuo Lin, Quan-Ling Liu, Yi Yang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD

Direct On-Policy Distillation (Direct-OPD) transfers reinforcement-learning-induced policy improvements from a small model to a larger student by using the token-level log-ratio between post-RL and pre-RL checkpoints as dense supervision on the student's own rollouts. This transfer rewards the policy shift at every sta...

Yibo Zhao, Zi-Xuan Yang, Yun-Shi Lan et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation

This work identifies Teacher Uncertainty Contraction (TUC), a systematic phenomenon whereby the teacher's predictive uncertainty decreases as it continues from a student-generated prefix, and proposes Adaptive-Continuations On-Policy Distillation (AC-OPD), which augments informative states along student rollouts with t...

Jin-Gang Zhou, Yu-Yi Zhou, Hai-Yang Guo et al. · 3 citations
#natural language process... Preprint Oct 2026

Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards

Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have become two main paradigms for post-training reasoning models. RLVR gives each response a single outcome label, leaving the steps inside it without separate credit. OPD provides token-level guidance at student-visited prefixes, b...

Xiao-Bin Chen, Zhi-Qi Pang · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.