OpenClaw-RL: Train any agent simply by talking

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Awesome List for On-Policy Distillation

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

A curated collection of papers and resources on On-Policy Distillation for Large Language Models.

A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, on-policy (OPD), cross-tokenizer, multimodal, and on-policy self-distillation.

🔥 DanceOPD: On-Policy Generative Field Distillation

Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"

Tiny-R2: A hybrid architecture integrating SWA, CSA, HCA, mHC, and DSMoE under the DeepSeek V4 design paradigm, enabling single-GPU OPD post-training.

Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).

CaOPD: Calibration-Aware On-Policy Distillation

Weak-to-Strong Generalization via Direct On-Policy Distillation

A bilingual awesome list for VLM/MLLM knowledge injection research: benchmarks, papers, tools, resources, and ecosystem updates.

[ICML 2026] Official implementation of FA-OPD: Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher

A curated collection of papers, code, surveys, and resources on on-policy post-training for large language models, including online SFT, on-policy distillation, RLHF, RLVR, self-improvement, verifier-guided learning, and search-based training.

Crosslingual On-Policy Self-Distillation for Multilingual Reasoning

6 files · 650 lines of core code · Full implementation of On-Policy Distillation

Awesome On-Policy Distillation

Companion website for A Survey of On-Policy Distillation for Large Language Models (arXiv:2604.00626).

An evidence-backed research map and taxonomy of On-Policy Distillation (OPD) for LLMs, VLMs, and agents. Reinforcement Learning.