TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

• URL: http://arxiv.org/abs/2607.05804v1
• Date: Tue, 07 Jul 2026 03:56:35 GMT
• Title: TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
• Abstract summary: On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories.<n>We propose TurnOPD, a turn-level budgeting strategy for efficient on-policy distillation of long-horizon agents.
• Score: 52.6661804966136
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training. However, its application to long-horizon agentic tasks remains insufficiently explored. We identify two key inefficiencies in vanilla agent OPD: (1) full-horizon rollouts often waste wall-clock resources on tail turns that provide weak and noisy KL supervision, and (2) trajectory-level KL objectives concentrate most of the loss on shallow tokens, leaving deeper decision turns under-trained once initial behaviors are aligned. To address these challenges, we propose TurnOPD, a turn-level budgeting strategy for efficient on-policy distillation of long-horizon agents. TurnOPD consists of two budget controllers: adaptive rollout-depth budgeting, which uses probe-based turn statistics to determine rollout length, and progressive turn-normalized loss budgeting, which gradually shifts KL weighting from token-level to turn-balanced supervision. Experiments on ALFWorld, WebShop, and Multi-Hop Search with task-specialized teacher models show that TurnOPD achieves superior validation accuracy under equal wall-clock training budgets and advances the accuracy--time frontier beyond vanilla OPD.

Related papers

• TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents [51.523913302114266]
  TRACE (Turn-level Reward Assignment via Credit Estimation) is a dense credit-assignment method for agentic reinforcement learning.<n>It represents rollouts as state transitions at tool-call boundaries, obtains gold-answer log-probabilities from a frozen reference model, transforms them into log-ratio state values, and derives per-action rewards as Temporal-Difference changes in those values.<n>It substantially improves base-model tool-use ability using pure RL, without a cold-start supervised fine-tuning stage, an agentic mid-training stage, or training on live-web data.
  arXiv  Detail & Related papers  (2026-07-15T16:16:42Z)
• ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents [6.4535223115254885]
  Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement.<n>We propose ATOD (Annealed Turn-aware On-policy Distillation), a hybrid online distillation algorithm that explicitly exploits this complementarity.
  arXiv  Detail & Related papers  (2026-06-26T07:56:32Z)
• 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)
• Are Full Rollouts Necessary for On-Policy Distillation? [63.18243901591995]
  On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts.<n>We identify the rollout horizon as a key bottleneck in OPD that substantially impacts training efficiency.<n>We propose two simple horizon-control strategies: Progressive OPD, which gradually expands the rollout horizon during training, and Truncated OPD, which permanently performs distillation on reliable truncated rollouts.
  arXiv  Detail & Related papers  (2026-05-29T16:12:54Z)
• 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)
• 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)
• Training Multi-Turn Search Agent via Contrastive Dynamic Branch Sampling [29.182538022605627]
  Branching Relative Policy Optimization (BranPO) is a value-free method that provides step-level contrastive supervision without dense rewards.<n>BranPO truncates trajectories near the tail and resamples alternative continuations to construct contrastive suffixes over shared prefixes.<n>To further boost efficiency and stabilize training, we introduce difficulty-aware branch sampling to adapt branching frequency across tasks, and redundant step masking to suppress uninformative actions.
  arXiv  Detail & Related papers  (2026-02-03T16:43:09Z)
• Beat the long tail: Distribution-Aware Speculative Decoding for RL Training [75.75462952580796]
  We propose a Distribution Aware Speculative decoding framework that accelerates RL rollouts without altering model outputs.<n>Experiments on math and code reasoning tasks show that DAS reduces rollout time up to 50% while preserving identical training curves.
  arXiv  Detail & Related papers  (2025-11-17T19:02:12Z)

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.