ChenxinAn-fdu / POLARISLinks
Scaling RL on advanced reasoning models
☆392Updated this week
Alternatives and similar repositories for POLARIS
Users that are interested in POLARIS are comparing it to the libraries listed below
Sorting:
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆412Updated last month
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆295Updated 3 weeks ago
- General Reasoner: Advancing LLM Reasoning Across All Domains☆147Updated last month
- The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆150Updated last week
- Code for the paper: "Learning to Reason without External Rewards"☆319Updated this week
- A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.☆157Updated this week
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆223Updated 2 months ago
- official repository for “Reinforcement Learning for Reasoning in Large Language Models with One Training Example”☆323Updated this week
- ReasonFlux Series - A family of LLM post-training algorithms focusing on data selection, reinforcement learning, and inference scaling☆447Updated last week
- ☆280Updated last month
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆163Updated this week
- Official implementation of the paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆179Updated last month
- ☆77Updated 3 months ago
- Efficient Agent Training for Computer Use☆111Updated last month
- Tina: Tiny Reasoning Models via LoRA☆266Updated last month
- A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning☆228Updated last month
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆216Updated 2 weeks ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆420Updated last month
- Scaling Data for SWE-agents☆283Updated this week
- Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"☆244Updated 2 months ago
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents☆190Updated 3 weeks ago
- ☆210Updated 4 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆226Updated 2 months ago
- ☆303Updated last month
- Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆85Updated 3 weeks ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆232Updated 10 months ago
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆268Updated 4 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆137Updated this week
- Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆566Updated 3 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆112Updated this week