■Bibliographic Information
Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim, Suhong Moon, Hiroki Furuta, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami. “Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks”. International Conference on Machine Learning (ICML).
■Overview
Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. Recent work has found success by separating high-level planning from low-level execution, which However, generating accurate plans remains difficult since LLMs are not a simple task. To address this, we propose Plan-and-Act, a novel framework that incorporates To address this, we propose Plan-and-Act, a novel framework that incorporates explicit planning into LLM-based agents and introduces a scalable method to enhance plan generation through a novel synthetic data generation method. Plan-and-Act consists of a Planner model which generates structured, high-level plans to achieve user goals, and an Executor model that translates these plans into environment-specific actions. To train the Planner effectively, we introduce a synthetic data generation method that annotates To train the Planner effectively, we introduce a synthetic data generation method that annotates ground-truth trajectories with feasible plans, augmented with diverse and extensive examples to enhance generalization. We evaluate Plan-and-Act using web navigation as a representative long-horizon planning environment, demonstrating a state-of-the-art 57.58% success rate on the WebArena- Lite benchmark as well as a text-only state-of-the-art 81.36% success rate on WebVoyager.
Our paper has been accepted by ICML.
