Framework for evaluating and improving agents
- evals
- rl-environments
- terminal-bench
Repository Index
69,734 visible repositories in the index
1–6 of 6 · Most stars
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.
Our library for RL environments + evals
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- agent
- artificial-intelligence
- benchmark
- multimodal
This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents