complex-reasoning / RPGLinks
Official implementation of Regularized Policy Gradient (RPG) (https://arxiv.org/abs/2505.17508)
☆40Updated this week
Alternatives and similar repositories for RPG
Users that are interested in RPG are comparing it to the libraries listed below
Sorting:
- ☆27Updated 3 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆34Updated last month
- ☆33Updated 8 months ago
- Resa: Transparent Reasoning Models via SAEs☆41Updated last week
- Official repo of paper LM2☆44Updated 7 months ago
- The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]☆32Updated last month
- Esoteric Language Models☆99Updated 2 months ago
- Reinforcing General Reasoning without Verifiers☆87Updated 3 months ago
- The official implementation of Self-Exploring Language Models (SELM)☆64Updated last year
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆100Updated last month
- ☆40Updated 3 months ago
- ☆20Updated 2 months ago
- Official Repo for InSTA: Towards Internet-Scale Training For Agents☆55Updated 2 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆59Updated last year
- A testbed for agents and environments that can automatically improve models through data generation.☆27Updated 7 months ago
- ☆85Updated last year
- A repository for research on medium sized language models.☆78Updated last year
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆98Updated last month
- ☆19Updated 7 months ago
- ☆48Updated 7 months ago
- ☆123Updated 7 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆77Updated 6 months ago
- ☆40Updated 4 months ago
- ☆77Updated 2 weeks ago
- EvaByte: Efficient Byte-level Language Models at Scale☆109Updated 5 months ago
- ☆21Updated this week
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆35Updated last year
- ☆23Updated last year
- SSRL: Self-Search Reinforcement Learning☆145Updated last month
- The original Shared Recurrent Memory Transformer implementation☆31Updated 2 months ago