SQLEnv
Step through an OpenEnv environment with custom actions
Spaces submitted for the UCB AgentBeats Hackathon OpenEnv special track.
Step through an OpenEnv environment with custom actions
Play a multi‑turn legal reasoning judge simulation
Reproducible multi-domain OpenEnv benchmark env.
OpenEnv benchmark for AI-assisted GPU inference scheduling
Train AI agents to play OpenRA RTS game
Benchmark LLM agents on robust data‑fetching tool use
Control and monitor datacenter scenarios via an interactive console
Step through a lottery elicitation environment
Explore a hospitality simulation by sending messages and tools
Play a physics‑based Carrom board game in your browser
Step through and view an OpenEnv simulation in a web UI
Explore multi‑tool queries and see step‑by‑step results
Generate actions in a MiniGrid environment
A PPO agent trained from scratch on 10 curriculum tracks.
Interact with temporal benchmark environment
Step through a search-economics simulation with custom actions