on-policy-learning

STAR-OPD is a novel on-policy distillation method for ABSA quadruple extraction that uses set-structured rewards to correct structural errors in student models, improving performance and narrowing the gap with teacher models.

This paper introduces HB-SJD, a batched speculative Jacobi decoding method for visual on-policy distillation that accelerates rollout generation by processing multiple tokens in parallel, reducing training time while preserving generation quality.

This paper proposes Tail-Aware Top-k On-Policy Distillation (TA-OPD) to address the loss of tail probability in on-policy distillation for language models, improving downstream accuracy on benchmarks.

This paper addresses rubric interference in LLM judges when evaluating multiple rubrics simultaneously and proposes Self-Anchored Rubric Alignment (SARA) to improve consistency through on-policy self-distillation.

DUET is a dual-teacher on-policy distillation method for ensuring LLMs comply with runtime prohibitions, achieving high violation compliance while preserving utility through token-selective learning.

The paper introduces S^2VOPD, a self-supervised method that improves vision-language models by distilling from original images into strongly augmented student views, achieving performance surpassing GPT-5.4 on benchmarks.

This paper introduces Latent On-Policy Self-Distillation (LOPD), a method that makes the teacher's privileged context learnable end-to-end from experience, providing dense token-level supervision to enhance agent performance and efficiency in agentic tool use and code generation.

Introduces Φ-Nav, a unified on-policy framework that uses hindsight reasoning to synthetically generate path-level instructions from exploratory trajectories, bridging the semantic supervision gap in Vision-Language Navigation and achieving competitive results on R2R-CE and RxR-CE benchmarks with fewer expert demonstrations.

OPRD proposes a new knowledge distillation method that aligns student and teacher hidden states across layers during on-policy rollouts, eliminating sampling variance from token-space KL estimation. Empirically, OPRD outperforms output-space baselines on math reasoning benchmarks (AIME 2024/2025, AIMO) while being 1.44x faster and using 54% less memory.

This paper introduces On-Policy Harness Self-Distillation (OPHSD), a method that internalizes the capabilities of inference-time reasoning harnesses into the base model through self-distillation. The approach improves standalone performance on complex reasoning tasks, allowing the model to retain reasoning scaffolds without permanent external dependencies.

This paper introduces ROPD, a rubric-based on-policy distillation framework that achieves superior sample efficiency compared to traditional logit-based methods. It enables model alignment in black-box scenarios by using structured semantic rubrics instead of teacher logits.

This paper introduces D-OPSD, a novel training paradigm for step-distilled diffusion models that enables on-policy self-distillation during supervised fine-tuning. It allows models to learn new concepts or styles without compromising their efficient few-step inference capabilities.

This paper introduces TESSY, a teacher-student cooperative framework for fine-tuning reasoning models that generates on-policy SFT data by decoupling generation into capability tokens (from teacher) and style tokens (from student), addressing catastrophic forgetting issues when using off-policy teacher data.