L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
☆264May 14, 2025Updated last year
Alternatives and similar repositories for l1
Users that are interested in l1 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆75Apr 13, 2025Updated last year
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆100Feb 21, 2025Updated last year
- ☆17Apr 11, 2025Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆463Mar 20, 2026Updated 4 months ago
- Official Repo for Open-Reasoner-Zero☆2,097Jun 2, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Democratizing Reinforcement Learning for LLMs☆5,784Updated this week
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆262Mar 7, 2026Updated 5 months ago
- Paper list for Efficient Reasoning.☆901May 29, 2026Updated 2 months ago
- Official Repo for SwS: A Weakness-driven Problem Synthesis Framework in RL for LLM Reasoning☆42Nov 11, 2025Updated 9 months ago
- ☆353May 24, 2025Updated last year
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆786Feb 28, 2026Updated 5 months ago
- Simple RL training for reasoning☆3,869Dec 23, 2025Updated 7 months ago
- ☆766Dec 23, 2025Updated 7 months ago
- Scalable RL solution for advanced reasoning of language models☆1,868Mar 18, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- This repository includes a benchmark and code for the paper "Evaluating LLMs at Detecting Errors in LLM Responses".☆32Aug 18, 2024Updated last year
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,855May 11, 2025Updated last year
- ☆187Dec 5, 2025Updated 8 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆127May 6, 2025Updated last year
- [NeurIPS 2025] Thinkless: LLM Learns When to Think☆261Sep 26, 2025Updated 10 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,271Aug 27, 2025Updated 11 months ago
- ☆221Feb 20, 2025Updated last year
- ☆224Mar 26, 2025Updated last year
- ☆65Mar 30, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆227Nov 30, 2025Updated 8 months ago
- [NeurIPS 2025] TTRL: Test-Time Reinforcement Learning☆1,110Apr 15, 2026Updated 4 months ago
- [ICML 2025] Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search☆114Jun 3, 2025Updated last year
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆30Aug 9, 2025Updated last year
- ☆336May 31, 2025Updated last year
- Awesome-Parallel-Reasoning: Unlocking the reasoning potential of LLMs. Papers, Code, Resources & Survey.☆55Mar 8, 2026Updated 5 months ago
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆288Feb 19, 2025Updated last year
- [COLM 2025] LIMO: Less is More for Reasoning☆1,083Jul 30, 2025Updated last year
- ☆1,177Jan 10, 2026Updated 7 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.
- [AAAI 2026] - Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"☆292Mar 11, 2026Updated 5 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,769Jul 24, 2026Updated 3 weeks ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆165Jun 22, 2026Updated last month
- ☆811Jun 9, 2025Updated last year
- A version of verl to support diverse tool use [TMLR 2026]☆1,030Jul 15, 2026Updated last month
- Source code for our paper: "Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents".☆25Feb 20, 2026Updated 5 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆449Jul 11, 2025Updated last year