Robotouille: An Asynchronous Planning Benchmark for LLM Agents
This addresses the problem of limited evaluation for asynchronous planning in LLM agents, which is incremental as it builds on existing benchmarks by adding new datasets and complexity.
The authors tackled the lack of benchmarks for evaluating asynchronous planning in LLM agents by introducing Robotouille, a challenging environment that tests long-horizon scenarios, where ReAct (gpt4-o) achieved 47% on synchronous tasks but only 11% on asynchronous tasks.
Effective asynchronous planning, or the ability to efficiently reason and plan over states and actions that must happen in parallel or sequentially, is essential for agents that must account for time delays, reason over diverse long-horizon tasks, and collaborate with other agents. While large language model (LLM) agents show promise in high-level task planning, current benchmarks focus primarily on short-horizon tasks and do not evaluate such asynchronous planning capabilities. We introduce Robotouille, a challenging benchmark environment designed to test LLM agents' ability to handle long-horizon asynchronous scenarios. Our synchronous and asynchronous datasets capture increasingly complex planning challenges that go beyond existing benchmarks, requiring agents to manage overlapping tasks and interruptions. Our results show that ReAct (gpt4-o) achieves 47% on synchronous tasks but only 11% on asynchronous tasks, highlighting significant room for improvement. We further analyze failure modes, demonstrating the need for LLM agents to better incorporate long-horizon feedback and self-audit their reasoning during task execution. Code is available at https://github.com/portal-cornell/robotouille.