Robotouille

The 'Robotouille' dataset/benchmark is used to evaluate the performance of large language models on long-horizon tasks that require multi-step reasoning and dynamic re-planning.

Papers using Robotouille (3)

ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents2025 · 6 citesRobotouille: An Asynchronous Planning Benchmark for LLM Agents2025Query-Efficient Planning with Language Models2024