zhourunlong / Reflect-RLLinks
Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
☆18Updated 5 months ago
Alternatives and similar repositories for Reflect-RL
Users that are interested in Reflect-RL are comparing it to the libraries listed below
Sorting:
- Natural Language Reinforcement Learning☆101Updated 5 months ago
- Bayes-Adaptive RL for LLM Reasoning☆42Updated 7 months ago
- ☆32Updated last year
- Dateset Reset Policy Optimization☆31Updated last year
- The official repository of "SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World".☆27Updated 4 months ago
- ☆31Updated last year
- ☆116Updated 11 months ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆47Updated last year
- Directional Preference Alignment☆58Updated last year
- This is the repository for paper EscapeBench: Pushing Language Models to Think Outside the Box☆17Updated last year
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆70Updated 9 months ago
- ☆75Updated last month
- ☆65Updated 9 months ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆57Updated last year
- Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)☆159Updated last year
- GenRM-CoT: Data release for verification rationales☆67Updated last year
- ☆107Updated last year
- Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF☆24Updated last year
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆46Updated 8 months ago
- Official code for the paper: WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents☆55Updated 3 weeks ago
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆32Updated last year
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆183Updated 7 months ago
- ☆51Updated 10 months ago
- PreAct: Prediction Enhances Agent's Planning Ability (Coling2025)☆30Updated last year
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆48Updated 7 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆113Updated 5 months ago
- Reinforced Multi-LLM Agents training☆63Updated 6 months ago
- ☆29Updated 9 months ago
- Verlog: A Multi-turn RL framework for LLM agents☆67Updated last week
- ☆35Updated 9 months ago