Trust Region On-Policy Distillation

• URL: http://arxiv.org/abs/2606.01249v2
• Date: Wed, 03 Jun 2026 04:57:08 GMT
• Title: Trust Region On-Policy Distillation
• Abstract summary: 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.
• Score: 38.98697509635889
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-Policy Distillation (OPD) is a fundamental technique for efficient post-training of large language models (LLMs), with broad applications in agent learning, multi-task enhancement, and model compression. However, OPD training becomes unstable when the teacher and student distributions differ substantially, as teacher supervision on student-generated tokens may yield unreliable policy gradients and even cause optimization failure. This work addresses reliable on-policy token-level supervision through credit assignment strategies, and proposes Trust Region On-Policy Distillation, TrOPD. It features the following characteristics: 1) Trust-Region On-Policy Learning: TrOPD performs OPD only in regions where the teacher provides reliable supervision, mitigating the optimization difficulty of the K1 reverse-KL estimator under distribution mismatch. 2) Outlier Estimation: For outlier regions, we explore gradient clipping, masking, and forward-KL estimation to reduce the adverse effects of unreliable supervision. 3) Off-Policy Guidance: The student continues generation from teacher prefixes and uses forward KL to imitate off-policy guidance, encouraging on-policy exploration toward reliable regions. Experiments show that TrOPD consistently outperforms SoTA OPD baselines, including OPD, EOPD, and REOPOLD, across mathematical reasoning, code generation, and general-domain benchmarks.

Related papers

• 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)
• Extreme Region Policy Distillation [36.61472284280031]
  We show that aggressive multi-step optimization brings rapid initial gains, but excessive updates cause trajectory probabilities to deviate and entropy to collapse.<n>This motivates Extreme Region Policy Distillation (ERPD), a two-stage framework that decouples sample efficiency from KL efficiency.
  arXiv  Detail & Related papers  (2026-05-25T08:32:24Z)
• 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)
• 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)
• Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe [53.40076304466524]
  We propose Uni-OPD, a unified OPD framework that generalizes across Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs)<n>Specifically, from the student's perspective, we adopt two data balancing strategies to promote exploration of informative student-generated states during training.<n>We develop an outcome-guided margin calibration mechanism to restore order consistency between correct and incorrect trajectories.
  arXiv  Detail & Related papers  (2026-05-05T12:15:21Z)
• TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents [55.27396165691312]
  We identify a key limitation of vanilla OPD in multi-turn agent settings, which we term Trajectory-Level KL Instability.<n>We propose TCOD, a framework that controls the trajectory depth exposed to the student and progressively expands it with a curriculum schedule.<n> Experimental results across four student-teacher pairs show that TCOD mitigates KL escalation and enhances KL stability throughout training, improving agent performance by up to 18 points over vanilla OPD.
  arXiv  Detail & Related papers  (2026-04-27T03:38:27Z)
• SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting [17.504616835765617]
  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.
  arXiv  Detail & Related papers  (2026-04-12T15:26:14Z)
• Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction [73.77593805292194]
  We train a separate exploration policy to maximize an approximate upper confidence bound of the critics in an off-policy actor-critic framework. To mitigate the off-policy-ness, we adapt the recently introduced DICE framework to learn a distribution correction ratio for off-policy actor-critic training.
  arXiv  Detail & Related papers  (2021-10-22T22:07:51Z)

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.