🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
☆639Jan 29, 2026Updated last month
Alternatives and similar repositories for oat
Users that are interested in oat are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,232Aug 27, 2025Updated 6 months ago
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆249Apr 15, 2025Updated 11 months ago
- Official Repo for Open-Reasoner-Zero☆2,086Jun 2, 2025Updated 9 months ago
- A Gym for Agentic LLMs☆467Jan 21, 2026Updated 2 months ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆24May 20, 2025Updated 10 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆53Jul 15, 2025Updated 8 months ago
- Scalable RL solution for advanced reasoning of language models☆1,821Mar 18, 2025Updated last year
- Simple RL training for reasoning☆3,841Dec 23, 2025Updated 3 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆83Oct 23, 2024Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆42Dec 29, 2025Updated 2 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,231Updated this week
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆382Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,259Updated this week
- 🔱 Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs☆71Mar 21, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆334May 31, 2025Updated 9 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆47Apr 15, 2025Updated 11 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆20,097Updated this week
- ☆1,113Jan 10, 2026Updated 2 months ago
- ☆20Apr 16, 2025Updated 11 months ago
- Reproducing R1 for Code with Reliable Rewards☆297May 5, 2025Updated 10 months ago
- AllenAI's post-training codebase☆3,643Updated this week
- Recipes to train reward model for RLHF.☆1,521Apr 24, 2025Updated 11 months ago
- Reinforcing General Reasoning without Verifiers☆97Jun 24, 2025Updated 9 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,553Mar 15, 2026Updated last week
- Scalable toolkit for efficient model reinforcement☆1,447Updated this week
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆135Mar 21, 2025Updated last year
- Repo of paper "Free Process Rewards without Process Labels"☆170Mar 14, 2025Updated last year
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆652Jul 29, 2025Updated 7 months ago
- Async RL Training at Scale☆1,176Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,699Mar 18, 2026Updated last week
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,762May 11, 2025Updated 10 months ago
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆679Mar 16, 2025Updated last year
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- triton ver of gqa flash attn, based on the tutorial☆12Aug 4, 2024Updated last year
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆179Sep 18, 2025Updated 6 months ago
- ☆356Jul 29, 2025Updated 7 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆123May 6, 2025Updated 10 months ago
- Our library for RL environments + evals☆3,918Updated this week
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆224Nov 27, 2025Updated 3 months ago
- AnchorAttention: Improved attention for LLMs long-context training☆216Jan 15, 2025Updated last year