One STEP at a time: Language Agents are Stepwise Planners
This addresses the planning bottleneck for language agents in dynamic environments, representing a strong specific gain rather than a broad breakthrough.
The paper tackled the problem of language agents falling short in tasks requiring planning by introducing the STEP framework, which learns from previous experiences to enhance planning, achieving an overall score of 67.4 and completing 12 out of 18 tasks on the ScienceWorld benchmark.
Language agents have shown promising adaptability in dynamic environments to perform complex tasks. However, despite the versatile knowledge embedded in large language models, these agents still fall short when it comes to tasks that require planning. We introduce STEP, a novel framework designed to efficiently learn from previous experiences to enhance the planning capabilities of language agents in future steps. Concretely, STEP functions through four interconnected components. First, the Planner takes on the task, breaks it down into subtasks and provides relevant insights. Then the Executor generates action candidates, while the Evaluator ensures the actions align with learned rules from previous experiences. Lastly, Memory stores experiences to inform future decisions. In the ScienceWorld benchmark, our results show that STEP consistently outperforms state-of-the-art models, achieving an overall score of 67.4 and successfully completing 12 out of 18 tasks. These findings highlight STEP's potential as a framework for enhancing planning capabilities in language agents, paving the way for more sophisticated task-solving in dynamic environments.