SOD: Step-wise On-policy Distillation for Small Language Model Agents

• URL: http://arxiv.org/abs/2605.07725v1
• Date: Fri, 08 May 2026 13:30:42 GMT
• Title: SOD: Step-wise On-policy Distillation for Small Language Model Agents
• Abstract summary: Tool-integrated reasoning is difficult to scale to small language models.<n>Recently, on-policy distillation has gained popularity by supplying dense token-level supervision from a teacher.<n>We propose SOD, a step-wise on-policy distillation framework for small language model agents.
• Score: 32.49707795291693
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity. While reinforcement learning methods like group relative policy optimization provide only sparse outcome-level rewards. Recently, on-policy distillation (OPD) has gained popularity by supplying dense token-level supervision from a teacher on student-generated trajectories. However, our experiments indicate that applying OPD to TIR leads to a critical failure mode: erroneous tool calls tend to cascade across subsequent reasoning steps, progressively amplifying student-teacher divergence and rendering the teacher's token-level supervision increasingly unreliable. To address this, we propose SOD, a step-wise on-policy distillation framework for small language model agents, which adaptively reweights distillation strength at each step based on step-level divergence. Therefore, SOD can attenuate potentially misleading teacher signals in high-divergence regions while preserving dense guidance in well-aligned states. Experiments on challenging math, science, and code benchmarks show that SOD achieves up to 20.86% improvement over the second-best baseline. Notably, our 0.6B student achieves 26.13% on AIME 2025, demonstrating effective transfer of agentic reasoning to lightweight models. Our code is available at https://github.com/YoungZ365/SOD.

Related papers

• Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning [25.14117376141824]
  On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories.<n>Standard token-level OPD can provide only fragmented corrections along an erroneous student trajectory.<n>We propose emphStep-Level On-Policy Distillation (SOPD), which combines the long-horizon correction of supervised fine-tuning with the on-policy advantage of OPD.
  arXiv  Detail & Related papers  (2026-08-17T09:37:39Z)
• dOPSD: On-Policy Self-Distillation for Diffusion Language Models [52.60302464420127]
  Diffusion large language models generate text by iteratively denoising a masked sequence.<n>Supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards.<n>On-policy self-distillation (OPSD) offers a promising alternative, using one model as both student and teacher.
  arXiv  Detail & Related papers  (2026-07-05T17:47:29Z)
• On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents [50.78688247330029]
  On-Policy Distillation (OPD) is a natural recipe for transferring such capabilities to smaller students.<n>We propose Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout.<n>Guided-OPD improves Score by 21.1% and Success Rate by 25.5% over vanilla OPD on average.
  arXiv  Detail & Related papers  (2026-06-14T16:41:45Z)
• Trajectory-Refined Distillation [25.346810464266497]
  Trajectory-Refined Distillation (TRD) is a trajectory-level correction method that revises the student's rollout under the teacher guidance while within on-policy support.<n> TRD can also be applied to on-policy self-distillation (OPSD), a parameter-sharing variant that uses the student model conditioned on privileged informations as the teacher.
  arXiv  Detail & Related papers  (2026-06-07T03:17:25Z)
• 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)
• SODA: Semi On-Policy Black-Box Distillation for Large Language Models [19.748920924563546]
  Black-box knowledge distillation for large language models presents a strict trade-off.<n>Semi evaluations across four compact Qwen2.5 and Llama-3 models validate this semi on-policy paradigm.<n>It achieves this superior distillation quality while training 10 times faster, consuming 27% less peak GPU memory, and completely eliminating adversarial instability.
  arXiv  Detail & Related papers  (2026-04-04T21:38:22Z)
• Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion [84.20493238687187]
  We introduce a novel framework that moves beyond simple mimicry to instill a deeper conceptual understanding.<n>underlinetextitFirst, to address pattern memorization, Explanatory Inversion (EI) generates targeted explanatory probes''<n>underlinetextitSecond, to improve generalization, Explanatory GRPO (texttEXGRPO) uses a reinforcement learning algorithm with a novel Dialogue Structure Utility Bonus.
  arXiv  Detail & Related papers  (2026-02-26T23:01:46Z)
• OVD: On-policy Verbal Distillation [47.727229201069555]
  On-policy Verbal Distillation (OVD) is a memory-efficient framework that replaces token-level probability matching with trajectory matching.<n>OVD dramatically reduces memory consumption while enabling on-policy distillation from teacher models with verbal feedback.
  arXiv  Detail & Related papers  (2026-01-29T16:48:14Z)
• Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator [81.81748032199813]
  Diffusion models have demonstrated excellent performance for real-world image super-resolution (Real-ISR)<n>We propose a new One-Step textbfDiffusion model with a larger-scale textbfDiscriminator for SR.<n>Our discriminator is able to distill noisy features from any time step of diffusion models in the latent space.
  arXiv  Detail & Related papers  (2024-10-05T16:41:36Z)
• Distilling Object Detectors with Task Adaptive Regularization [97.52935611385179]
  Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization.
  arXiv  Detail & Related papers  (2020-06-23T15:58:22Z)

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.