The paper examines on‑policy self‑distillation, where a teacher scores a student’s rollout to provide dense token‑level credit. Experiments show that the raw scoring signals neither localize errors nor effectively penalize incorrect tokens, because locating errors is a search problem that the teacher is not explicitly asked to perform. Introducing a critique‑conditioned approach—first generating a critique of the rollout and then conditioning the teacher on it—produces signals that accurately localize errors, correct erroneous spans, and guide the policy toward backtracking tokens, improving performance on math problems and in cold‑start GRPO settings.
arXiv:2608. 04794v1 Announce Type: new Abstract: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it.
arXiv:2608. 09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses.
arXiv:2606. 15576v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards assigns a single scalar to each rollout, leaving token-level credit assignment underspecified in long reasoning traces.
Reinforcement learning from verifiable rewards assigns a single scalar to each rollout, leaving token-level credit assignment underspecified in long reasoning traces. On-policy self-distillation addresses this by letting the same model act as a teacher conditioned on privileged information, producing a dense per-token signal.
arXiv:2610.27467v1 Announce Type: cross Abstract: On-policy learning is central to post-training: training on a model's own generations limits distribution shift and helps preserve existing capabilit...
arXiv:2606. 11173v1 Announce Type: new Abstract: Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response.
arXiv:2606. 18810v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps.
arXiv:2605.28791v2 Announce Type: replace-cross Abstract: On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes in...
arXiv:2608. 09263v1 Announce Type: new Abstract: Outcome verifiers score completed reasoning traces but do not assign credit to intermediate tokens.
GR-OPD introduces Group-Relative On-Policy Distillation, which separates feedback computation from credit assignment by aggregating token feedback into calibrated sequence-level credit. The method shows that broadcasting summed feedback to all response tokens provides an unbiased estimate of the negative gradient of the sequence-level reverse‑KL objective under ideal on‑policy assumptions. In practice, GR‑OPD discounts later feedback to mitigate distribution shift, uses same‑prompt rollout groups for calibration, and retains a controlled fraction of collective teacher pressure, leading to superior performance over vanilla OPD across multiple Qwen3 teacher‑student settings and mathematical reasoning benchmarks.
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps. Existing token-level credit assignment methods require resources beyond the model's own rollouts.
arXiv:2605. 09253v2 Announce Type: replace-cross Abstract: While recent work in Reinforcement Learning with Verifiable Rewards (RLVR) has shown that a small subset of critical tokens disproportionately drives reasoning gains, an analogous token-level understanding of On-Policy Distillation (OPD) remains largely unexplored.