[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
☆1,063Aug 20, 2026Updated 2 months ago
Alternatives and similar repositories for Rethinking-OPD
Users that are interested in Rethinking-OPD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Awesome List for On-Policy Distillation☆882Oct 18, 2026Updated 2 weeks ago
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆301May 28, 2026Updated 5 months ago
- ☆701Sep 5, 2026Updated last month
- A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models☆905Oct 6, 2026Updated 3 weeks ago
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example☆98Sep 4, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Reinforcement Learning via Self-Distillation (SDPO)☆1,141Jul 1, 2026Updated 4 months ago
- A curated collection of papers and resources on On-Policy Distillation for Large Language Models.☆592Oct 13, 2026Updated 3 weeks ago
- [COLM 2026] Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes☆144May 19, 2026Updated 5 months ago
- On Policy Distillation Build on top of Verl☆106Sep 3, 2026Updated 2 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,091Updated this week
- ☆726Apr 7, 2026Updated 6 months ago
- slime is an LLM training framework for RL Scaling.☆8,774Oct 27, 2026Updated last week
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆2,420Jun 9, 2026Updated 4 months ago
- OPRD: On-Policy Representation Distillation (https://arxiv.org/abs/2606.06021)☆85Sep 9, 2026Updated last month
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, full vocab on-policy (OPD), cross-tokenizer…☆255Updated this week
- Official code for "Self-Distilled Agentic Reinforcement Learning"☆376Oct 15, 2026Updated 2 weeks ago
- Vision-OPD is a regional-to-global on-policy self-distillation framework that transfers a model's own privileged crop-conditioned percept…☆347Sep 27, 2026Updated last month
- [COLM 2026]TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents☆117Jul 9, 2026Updated 3 months ago
- Official Repo of "Flow-OPD: On-Policy Distillation for Flow Matching Models"☆313Jun 24, 2026Updated 4 months ago
- Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"☆115Sep 14, 2026Updated last month
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe☆57Jun 10, 2026Updated 4 months ago
- Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation☆115Aug 20, 2026Updated 2 months ago
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆5,560Nov 13, 2025Updated 11 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,209Sep 19, 2026Updated last month
- ☆89May 8, 2026Updated 5 months ago
- RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios☆659Jun 12, 2026Updated 4 months ago
- Weak-to-Strong Generalization via Direct On-Policy Distillation☆96Aug 18, 2026Updated 2 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,136Oct 5, 2026Updated 3 weeks ago
- ☆69Oct 16, 2026Updated 2 weeks ago
- [ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe☆309Updated this week
- Code of Self-Distilled RLVR - RLSD☆84May 19, 2026Updated 5 months ago
- ☆1,918Jun 18, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).☆38Jul 31, 2026Updated 3 months ago
- PyTorch-based open-source code for paper "SOD: Step-wise On-policy Distillation for Small Language Model Agents"☆166May 22, 2026Updated 5 months ago
- [NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning☆1,025Sep 25, 2026Updated last month
- [ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)☆1,143Oct 11, 2026Updated 3 weeks ago
- ☆1,284Nov 20, 2025Updated 11 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,443Updated this week
- A Survey of Reinforcement Learning for Large Reasoning Models☆2,498Sep 14, 2026Updated last month