Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation

• URL: http://arxiv.org/abs/2608.09826v1
• Date: Mon, 10 Aug 2026 16:43:18 GMT
• Title: Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation
• Abstract summary: Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong.<n>We propose SKALD (Skill-Anchored Latent Distillation), an on-policy self-distillation framework that uses two context views of the same Qwen3-Base model.
• Score: 7.296659715681798
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63.0-68.0% of groups in our experiments. We propose SKALD (Skill-Anchored Latent Distillation), an on-policy self-distillation framework that uses two context views of the same Qwen3-Base model: a question-only student and a teacher conditioned on an abstract, explicit-answer-filtered skill card. The student is trained on its own prefixes, transferring the skill-induced advantage into shared parameters without privileged input at test time. To stabilize context-induced distribution mismatch, SKALD employs an annealed exponentially tilted objective that downweights teacher-preferred tokens with very low student likelihood; as the tilt vanishes, it converges to teacher cross-entropy and recovers the forward-KL student gradient. An empirical gate activates distillation only when verified rollouts estimate a positive teacher advantage. Across five held-out mathematics benchmarks, SKALD improves overall avg@8 over GRPO by +2.46, +4.85, and +12.01 at 0.6B, 1.7B, and 4B, respectively. At 1.7B, zero-variance-only distillation recovers 84.7% of the full gain, while SKALD remains +4.06 above FLOP-matched GRPO and exceeds contextual skill exposure by +3.77. These results show that abstract skills provide dense supervision where group-relative rewards become uninformative.

Related papers

• On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following Rerankers [0.0]
  We revisit reranker distillation through the lens of reinforcement learning.<n>We propose a two-stage framework combining off-policy teacher optimization with on-policy student distillation.
  arXiv  Detail & Related papers  (2026-09-01T23:36:19Z)
• A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation [59.43605629311855]
  We analyze the gradient of the per-token K2 estimator of reverse KL with respect to the student logits.<n>Our primary contribution is therefore a gradient-level characterization of reverse-KL OPD trained with the K2 estimator, with SuRe as one empirical instantiation.
  arXiv  Detail & Related papers  (2026-08-26T11:14:42Z)
• WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training [48.290951447286744]
  WDL-OPD is a mixture-constrained co-training method with two trainable policies.<n>An anchor policy generates every rollout, an auxiliary policy evaluates the same visited states, and a geometric mixture of their token distributions is matched to a frozen teacher by reverse KL.<n>We show that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express.
  arXiv  Detail & Related papers  (2026-08-10T11:22:53Z)
• Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance [50.77757355236912]
  We propose RSTG (Recovering Learning Signals via Adaptive Teacher Guidance), which applies distillation selectively and precisely where it matters most.<n> Experiments demonstrate that RSTG substantially outperforms naive GRPO+OPD by +4.02% on math and+3.05% on code.
  arXiv  Detail & Related papers  (2026-08-01T17:29:14Z)
• Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning [55.264863369127774]
  Current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.<n>We propose Hidden-Align, an auxiliary loss function that aligns the last-layer hidden states of correct rollouts at the anchor token during RL training, with zero overhead in both training and inference.<n>On eight mathematical reasoning benchmarks, Hidden-Align improves average pass@1 over the DAPO baseline by 3.8, 6.2, and 5.4 percentage points on Qwen3-1.7B, 4B, and 14B respectively, with consistent pass@k gains across all three scales.
  arXiv  Detail & Related papers  (2026-06-02T06:51:15Z)
• CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO [9.443660785229719]
  Reinforcement learning with verifiable rewards (RLVR) has been widely used to improve reasoning in large language models.<n>This work proposes CAST, an answer-free self-distillation method for GRPO-style RLVR.
  arXiv  Detail & Related papers  (2026-05-29T13:21:30Z)
• Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation [81.10000755917712]
  On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher.<n>As student-generated prefixes lengthen, the teacher's next-token distribution becomes less confident and less discriminative.<n>To mitigate SFD, we introduce textbfLookahead Group Reward (ours).
  arXiv  Detail & Related papers  (2026-05-29T04:39:20Z)
• Skill-Conditioned Gated Self-Distillation for LLM Reasoning [22.02868419200851]
  On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense token-level supervision.<n>We propose Skill-Conditioned Gated Self-Distillation (SGSD), which formulates skill-based SD as teacher hypothesis validation rather than unconditional imitation.
  arXiv  Detail & Related papers  (2026-05-27T17:49:52Z)
• When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning [45.79647925282674]
  On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher.<n>Existing entropy-based OPD methods relax this uniformity by modulating token-level supervision with teacher entropy.<n>We propose Position-Weighted On-Policy Self-Distillation (PW-OPSD), which applies an increasing position weight while keeping the same student rollout, privileged teacher pass, and clipped forward-KL target as OPSD.
  arXiv  Detail & Related papers  (2026-05-20T18:14:03Z)
• Self-Distilled Agentic Reinforcement Learning [65.24201057390938]
  Self-Distilled Agentic Reinforcement Learning maps detached token-level signals into a sigmoid gate.<n>SDAR consistently outperforms hybrid RL--OPSD baselines across model scales.
  arXiv  Detail & Related papers  (2026-05-14T17:51:26Z)
• Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix Works [19.92945464084119]
  Group Relative Policy Optimization (GRPO) is a standard algorithm for reinforcement learning from verifiable rewards.<n>We prove that the true degeneracy rate always exceeds the i.i.d. Bernoulli prediction by Jensen's inequality.<n>We show that the fixed-reference Sign advantage, $A=2r-1$, performs pass@$G$ failure descent by increasing the probability that at least one sample in the group succeeds.
  arXiv  Detail & Related papers  (2026-05-08T12:58:06Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)

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.