balrog-ai / BALROGLinks
Benchmarking Agentic LLM and VLM Reasoning On Games
☆179Updated 2 weeks ago
Alternatives and similar repositories for BALROG
Users that are interested in BALROG are comparing it to the libraries listed below
Sorting:
- ☆99Updated last year
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆167Updated 2 months ago
- A Gym for Generalist LLMs☆48Updated this week
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆225Updated this week
- Bootstrapping ARC☆139Updated 8 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆149Updated 6 months ago
- 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
- ☆118Updated 5 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆59Updated 3 months ago
- Intrinsic Motivation from Artificial Intelligence Feedback☆130Updated last year
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆280Updated 3 weeks ago
- ☆172Updated 3 months ago
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆321Updated 8 months ago
- Can Language Models Solve Olympiad Programming?☆119Updated 6 months ago
- ☆184Updated last year
- ☆95Updated 3 months ago
- ☆137Updated 2 weeks ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆44Updated last year
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆226Updated 2 weeks ago
- Learn online intrinsic rewards from LLM feedback☆42Updated 7 months ago
- [ICLR 2025] "Training LMs on Synthetic Edit Sequences Improves Code Synthesis" (Piterbarg, Pinto, Fergus)☆19Updated 5 months ago
- ☆143Updated last year
- ☆99Updated last year
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆236Updated 9 months ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆117Updated 3 months ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆61Updated 5 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆175Updated 4 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆105Updated 10 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 6 months ago
- Open source interpretability artefacts for R1.☆157Updated 3 months ago