balrog-ai / BALROGLinks
Benchmarking Agentic LLM and VLM Reasoning On Games
☆196Updated last month
Alternatives and similar repositories for BALROG
Users that are interested in BALROG are comparing it to the libraries listed below
Sorting:
- ☆101Updated last year
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆281Updated last week
- Verlog: A Multi-turn RL framework for LLM agents☆42Updated last week
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆174Updated 4 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 8 months ago
- A Gym for Generalist LLMs☆131Updated last week
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆140Updated last year
- Bootstrapping ARC☆142Updated 10 months ago
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆295Updated 2 months ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆239Updated 2 weeks ago
- Learn online intrinsic rewards from LLM feedback☆43Updated 9 months ago
- ☆123Updated 7 months ago
- ☆111Updated last week
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆230Updated 2 months ago
- Skill Design From AI Feedback☆31Updated 7 months ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆64Updated 7 months ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆151Updated 2 weeks ago
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆329Updated 10 months ago
- ☆100Updated last year
- Can Language Models Solve Olympiad Programming?☆118Updated 8 months ago
- ☆138Updated 2 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆63Updated 5 months ago
- ☆116Updated 8 months ago
- ☆144Updated last year
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆47Updated last year
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆129Updated last month
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆193Updated 5 months ago
- ☆186Updated last year
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆117Updated last year