AIFrameResearch / SPOLinks
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
☆37Updated 3 weeks ago
Alternatives and similar repositories for SPO
Users that are interested in SPO are comparing it to the libraries listed below
Sorting:
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆82Updated 4 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆86Updated 8 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆91Updated 7 months ago
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆69Updated 5 months ago
- ☆156Updated last week
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated 10 months ago
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆26Updated 8 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆258Updated 5 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆345Updated 3 months ago
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆81Updated 8 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆298Updated 3 weeks ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆46Updated 4 months ago
- Official Repository of LatentSeek☆64Updated 4 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆79Updated 3 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆112Updated 2 months ago
- ☆38Updated 2 months ago
- Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training☆39Updated last month
- Extrapolating RLVR to General Domains without Verifiers☆173Updated 2 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆106Updated 6 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆54Updated 4 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆69Updated 3 months ago
- TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25☆70Updated 4 months ago
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆137Updated 3 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆69Updated 6 months ago
- ☆297Updated 4 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆340Updated 2 weeks ago
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆57Updated 2 months ago
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆19Updated 3 weeks ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆133Updated 6 months ago
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆23Updated 2 months ago