SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting

• URL: http://arxiv.org/abs/2604.10688v1
• Date: Sun, 12 Apr 2026 15:26:14 GMT
• Title: SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
• Abstract summary: We propose a dual-path adaptive training framework that routes on-policy rollouts by correctness into two complementary supervision paths.<n>SCOPE achieves an average relative improvement of 11.42% in Avg@32 and 7.30% in Pass@32 over competitive baselines.
• Score: 17.504616835765617
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult. On-Policy Distillation (OPD) alleviates this by introducing dense, token-level KL supervision from a teacher model, but typically applies this supervision uniformly across all rollouts, ignoring fundamental differences in signal quality. We propose Signal-Calibrated On-Policy Distillation Enhancement (SCOPE), a dual-path adaptive training framework that routes on-policy rollouts by correctness into two complementary supervision paths. For incorrect trajectories, SCOPE performs teacher-perplexity-weighted KL distillation to prioritize instances where the teacher demonstrates genuine corrective capability, while down-weighting unreliable guidance. For correct trajectories, it applies student-perplexity-weighted MLE to concentrate reinforcement on low-confidence samples at the capability boundary rather than over-reinforcing already mastered ones. Both paths employ a group-level normalization to adaptively calibrate weight distributions, accounting for the intrinsic difficulty variance across prompts. Extensive experiments on six reasoning benchmarks show that SCOPE achieves an average relative improvement of 11.42% in Avg@32 and 7.30% in Pass@32 over competitive baselines, demonstrating its consistent effectiveness.

Related papers

• Adaptive Supervised Anchoring for On-Policy Self-Distillation [15.445625053566244]
  On-policy self-distillation adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student.<n>We show that when student rollouts drift from target trajectories, conditioning the teacher on off-target prefixes substantially weakens its task-relevant supervision.<n>We propose a unified training framework that separates two complementary supervision pathways.
  arXiv  Detail & Related papers  (2026-08-08T05:46:32Z)
• PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning [47.656931433805745]
  On-policy self-distillation provides dense token-level supervision from a privileged teacher.<n>Existing methods rely on isolated token-level discrepancies, which can be sensitive to noise.<n>We propose Consistency Persistent Self-Distillation (PCSD), which derives token-level distillation weights from the local persistence of teacher-favoring signals.
  arXiv  Detail & Related papers  (2026-08-03T07:47:59Z)
• 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)
• DOPD: Dual On-policy Distillation [59.65986569617147]
  On-policy distillation offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals.<n>We propose DOPD, an advantage-aware dual distillation paradigm that dynamically routes token-level supervision between privileged teacher and privileged student policies.<n>Experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that DOPD consistently outperforms Vanilla OPD.
  arXiv  Detail & Related papers  (2026-06-29T17:55:53Z)
• SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation [25.25989941933095]
  We propose SAGE-OPD, a verifier-free selective intervention framework specifically designed for multi-turn OPD.<n>Instead of applying teacher supervision uniformly across all turns, SAGE-OPD first observes environment feedback and uses teacher judgment to decide whether each student response should be skipped or intervened on.<n>Experiments on agent tasks show that SAGE-OPD consistently improves over baselines, achieving up to a 13.3% relative improvement in ALFWorld unseen success rate over standard OPD.
  arXiv  Detail & Related papers  (2026-06-17T23:58:14Z)
• Trust Region On-Policy Distillation [38.98697509635889]
  On-Policy Distillation (OPD) is a technique for efficient post-training of large language models.<n>This work addresses reliable on-policy token-level supervision through credit assignment strategies.<n>Experiments show that TrOPD consistently outperforms SoTA OPD baselines.
  arXiv  Detail & Related papers  (2026-05-31T14:04:51Z)
• 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)
• Teacher-Guided Policy Optimization for LLM Distillation [90.49982387646861]
  Teacher-Guided Policy Optimization (TGPO) is an on-policy algorithm that incorporates dense directional guidance by leveraging teacher predictions conditioned on the student's rollout.<n>Experiments on complex reasoning benchmarks demonstrate that TGPO significantly outperforms standard baselines and is robust to different teachers.
  arXiv  Detail & Related papers  (2026-05-13T09:20:03Z)
• OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning [19.98950359294245]
  We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories.<n>Despite the performance gains of OPSD, we identify a common but often overlooked mismatch between teacher and student responses.
  arXiv  Detail & Related papers  (2026-05-12T17:00:53Z)
• PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners [9.324642081509756]
  Large language model (LLM) reasoning requires supervision that is both aligned with the model's own test-time states and informative at the token level.<n>Recent privileged on-policy self-distillation explores a middle ground by scoring student rollouts with the same model under verified solution context.<n>We propose PAINT, which masks the verified solution according to rollout-reference overlap and applies a small energy-space on a sparse set of entropy-mismatch token positions.
  arXiv  Detail & Related papers  (2026-04-29T11:56:07Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing [79.88256756334327]
  Self-Distillation Policy Optimization (SDPO) addresses this by providing denser, more targeted logit-level supervision.<n>We propose Sample-Routed Policy Optimization (SRPO)<n>SRPO routes correct samples to GRPO's reward-aligned reinforcement and failed samples to SDPO's targeted logit-level correction.
  arXiv  Detail & Related papers  (2026-04-02T17:29:18Z)
• What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time [57.533031432715084]
  Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams.<n>Existing TTRL methods rely exclusively on positive pseudo-labeling strategies.<n>We propose SCRL, a robust test-time reinforcement learning framework that effectively mitigates label noise amplification.
  arXiv  Detail & Related papers  (2026-03-20T11:47:12Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training [11.136092421166097]
  Agentic RAG enhances large language models by incorporating external knowledge.<n>Current RL-based training methods suffer from sparse outcome rewards that discard intermediate signals.<n>We propose Search-P1, a framework that introduces path-centric reward shaping for agentic RAG training.
  arXiv  Detail & Related papers  (2026-02-26T03:31:00Z)
• GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning [55.03441672267886]
  We propose GradAlign, a gradient-aligned data selection method for reinforcement learning.<n>We evaluate GradAlign across three data regimes: unreliable reward signals, distribution imbalance, and low-utility training corpus.
  arXiv  Detail & Related papers  (2026-02-25T01:54:50Z)
• VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training [18.849117699859622]
  Training stability is a central challenge in reinforcement learning for large language models.<n>We propose Variational sEquence-level Soft Policy Optimization (VESPO)<n> Experiments on mathematical reasoning benchmarks show that VESPO maintains stable training under staleness ratios up to 64x and fully asynchronous execution.
  arXiv  Detail & Related papers  (2026-02-11T09:48:08Z)
• DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning [31.369103012768964]
  DISPO is a simple yet effective REINFORCE-style algorithm that decouples the up-clipping and down-clipping of importance sampling weights for correct and incorrect responses.<n>We show that DISPO achieves 61.04% on AIME'24 (vs. 55.42% CISPO and 50.21% DAPO) with similar gains across various benchmarks and models.
  arXiv  Detail & Related papers  (2026-02-01T02:45:04Z)
• KEPO: Knowledge-Enhanced Preference Optimization for Reinforcement Learning with Reasoning [24.072603982041798]
  Reinforcement learning has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models.<n>However, reasoning-oriented RL post-training remains fundamentally challenging due to sparse trajectory-level rewards.<n>Recent on-policy distillation methods introduce dense teacher supervision to stabilize optimization, but apply it uniformly across all generated trajectories.
  arXiv  Detail & Related papers  (2026-01-30T23:28:37Z)
• A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization [58.116300485427764]
  Reinforcement learning post-training can elicit reasoning behaviors in large language models.<n> token-level correction often leads to unstable training dynamics when the degree of off-policyness is large.<n>We propose a simple yet effective objective, Minimum Prefix Ratio (MinPRO)
  arXiv  Detail & Related papers  (2026-01-30T08:47:19Z)
• Stable On-Policy Distillation through Adaptive Target Reformulation [7.361248172930405]
  Veto is an objective-level reformulation that constructs a geometric bridge in the logit space.<n>Veto consistently outperforms supervised fine-tuning and existing on-policy baselines.
  arXiv  Detail & Related papers  (2026-01-12T02:57:39Z)
• AdaSwitch: Adaptive Switching Generation for Knowledge Distillation [58.647880811071495]
  Small language models (SLMs) are crucial for applications with strict latency and computational constraints.<n>We propose AdaSwitch, a novel approach that combines on-policy and off-policy generation at the token level.<n>AdaSwitch consistently improves accuracy, offering a practical and effective method for distilling SLMs with acceptable additional overhead.
  arXiv  Detail & Related papers  (2025-10-09T06:38:37Z)

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.