ChenxinAn-fdu / POLARISLinks
Scaling RL on advanced reasoning models
☆566Updated last week
Alternatives and similar repositories for POLARIS
Users that are interested in POLARIS are comparing it to the libraries listed below
Sorting:
- ReasonFlux Series - A family of LLM post-training algorithms focusing on data selection, reinforcement learning, and inference scaling☆481Updated 3 weeks ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆432Updated 3 months ago
- A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.☆605Updated 3 weeks ago
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆269Updated 6 months ago
- The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆161Updated last month
- ☆811Updated 2 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆248Updated 3 months ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆234Updated 3 months ago
- Code for the paper: "Learning to Reason without External Rewards"☆347Updated last month
- A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning☆244Updated 2 months ago
- ☆312Updated 2 months ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆441Updated 2 months ago
- official repository for “Reinforcement Learning for Reasoning in Large Language Models with One Training Example”☆347Updated 2 weeks ago
- Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"☆254Updated 3 months ago
- A version of verl to support tool use☆333Updated last week
- ✨ Agentic Reinforced Policy Optimization☆512Updated last week
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆170Updated last month
- Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆591Updated 5 months ago
- MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.☆251Updated this week
- ☆297Updated this week
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 4 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains☆163Updated 2 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆329Updated 2 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆438Updated this week
- Dream 7B, a large diffusion language model☆915Updated this week
- Tina: Tiny Reasoning Models via LoRA☆275Updated last week
- ☆271Updated 3 months ago
- ☆292Updated 2 months ago
- ☆206Updated 6 months ago
- Official implementation of the paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆213Updated last week