zwhong714 / PSFTLinks
PSFT is a trust-region–inspired fine-tuning objective that views SFT as a policy gradient method with constant advantages, constraining policy drift to stabilize training and improve generalization.
☆25Updated last week
Alternatives and similar repositories for PSFT
Users that are interested in PSFT are comparing it to the libraries listed below
Sorting:
- Scaling Preference Data Curation via Human-AI Synergy☆106Updated 2 months ago
- ☆75Updated last month
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆81Updated 3 months ago
- ☆18Updated 2 months ago
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models☆150Updated 3 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆128Updated 5 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 5 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆154Updated 3 weeks ago
- ☆127Updated 2 weeks ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆152Updated last week
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆149Updated 8 months ago
- This is a repo for showcasing using MCTS with LLMs to solve gsm8k problems☆87Updated 5 months ago
- MPO: Boosting LLM Agents with Meta Plan Optimization (EMNLP 2025 Findings)☆69Updated 3 weeks ago
- ☆149Updated 3 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated 9 months ago
- ☆39Updated 2 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 3 months ago
- IKEA: Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent☆64Updated 4 months ago
- ☆65Updated 9 months ago
- ☆165Updated 4 months ago
- ☆49Updated 6 months ago
- ☆103Updated 9 months ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆133Updated 2 months ago
- The demo, code and data of FollowRAG☆74Updated 2 months ago
- ☆209Updated 6 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆341Updated this week
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆141Updated 5 months ago
- The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆165Updated 2 months ago
- Extrapolating RLVR to General Domains without Verifiers☆158Updated last month
- ☆114Updated last year