balrog-ai / BALROGLinks
Benchmarking Agentic LLM and VLM Reasoning On Games
☆202Updated 2 months ago
Alternatives and similar repositories for BALROG
Users that are interested in BALROG are comparing it to the libraries listed below
Sorting:
- ☆104Updated last year
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆291Updated 3 weeks ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆178Updated 5 months ago
- A Gym for Agentic LLMs☆323Updated 2 weeks ago
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆142Updated last year
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 8 months ago
- ☆122Updated 8 months ago
- Verlog: A Multi-turn RL framework for LLM agents☆63Updated 2 weeks ago
- Bootstrapping ARC☆144Updated 11 months ago
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆299Updated 3 months ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆159Updated last month
- Learn online intrinsic rewards from LLM feedback☆43Updated 10 months ago
- Can Language Models Solve Olympiad Programming?☆119Updated 9 months ago
- [ICLR 2025] "Training LMs on Synthetic Edit Sequences Improves Code Synthesis" (Piterbarg, Pinto, Fergus)☆19Updated 8 months ago
- ☆138Updated 3 months ago
- ☆63Updated 7 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆64Updated 6 months ago
- ☆144Updated last year
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆65Updated 8 months ago
- ☆105Updated this week
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆330Updated 11 months ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆241Updated last week
- ☆116Updated 9 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆233Updated 3 months ago
- ☆113Updated last week
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆47Updated last year
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆196Updated 6 months ago
- ☆100Updated last year
- ☆184Updated last year