spiral-rl / spiralLinks
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
☆103Updated last week
Alternatives and similar repositories for spiral
Users that are interested in spiral are comparing it to the libraries listed below
Sorting:
- Code for "Reasoning to Learn from Latent Thoughts"☆112Updated 3 months ago
- Reinforcing General Reasoning without Verifiers☆71Updated 3 weeks ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆114Updated 2 months ago
- A repo for open research on building large reasoning models☆68Updated this week
- ☆61Updated 4 months ago
- ☆114Updated 5 months ago
- Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay☆88Updated last month
- Natural Language Reinforcement Learning☆90Updated 6 months ago
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆65Updated 3 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆39Updated last week
- ☆54Updated 2 weeks ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆100Updated last month
- 📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.☆86Updated this week
- [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study☆52Updated 7 months ago
- ☆96Updated 9 months ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆58Updated 4 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆108Updated 5 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆60Updated 5 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆98Updated 4 months ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆18Updated 3 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆166Updated last month
- ☆83Updated 2 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆33Updated 3 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆137Updated last week
- ☆98Updated last year
- ☆117Updated 4 months ago
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆82Updated last month
- Code for the paper: "Learning to Reason without External Rewards"☆319Updated this week
- The official implementation of Self-Exploring Language Models (SELM)☆64Updated last year
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆67Updated 2 months ago