paper-with-me

홈 › Papers

A Predictive Law for On-Policy Self-Distillation From World Feedback

2026-05-28 · Tommy He, Jerome Sieber, Matteo Saponati arxiv

Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPSD) is a promising recent approach that uses arbitrary feedback as learning signal, yet its reliability compared to established methods, such as GRPO, remains unclear. We identify a strikingly consistent linear correlation between the initial student-self-teacher performance gap and the final performance improvement in OPSD. This relationship holds across context types and model families, providing a powerful predictive law for anticipating the outcome of an OPSD configuration without running the full training procedure. Interestingly, we show that this linear predictability holds with model scale, suggesting a potential basis for new empirical scaling laws on larger models with stronger in-context learning capabilities. In essence, our findings show that OPSD performance can be predicted and tuned before training, offering a principled way to incorporate world feedback as a first-class component of the post-training pipeline.

📄 PDF Abstract BibTeX arXiv:2605.30070

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning from Language Feedback via Variational Policy Distillation

2026-05-14 · Yang Li, Erik Nijkamp, Semih Yavuz, Shafiq Joty arxiv

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address…

Reinforcement LearningMathematical ReasoningCode Generation

Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback

2026-06-12 · Woohyeon Byeon, Jiwon Jeon, Jeonghye Kim, Youngchul Sung arxiv

We study multi-domain LLM training in which two models, each stronger in a different domain, co-evolve by tutoring each other through on-policy feedback. Unlike one-way distillation or single-model fine-tuning, our goal …

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity

2026-06-24 · Andrei Liviu Nicolicioiu, Mohammad Pezeshki, Aaron Courville arxiv

On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a correct demonstration to provide dense token-level feedback. We show that…

Reinforcement Learning

Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts

2026-06-09 · Haoyu Dong arxiv

Code-generating large language models (LLMs) increasingly produce visual artifacts such as charts, web pages, and slides by writing programs that are executed by non-differentiable renderers, committing to code before ob…

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

2026-07-02 · Zhuowei Chen, Xiang Lorraine Li arxiv

Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Rece…

Domain GeneralizationOffline RL