HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidance
This addresses a critical bottleneck in LLM-based agents for complex decision-making tasks, though it appears incremental as it builds on existing hierarchical and retrieval-based methods.
The paper tackles the problem of LLM-based agents struggling with complex, long-horizon planning by introducing HiPlan, a hierarchical planning framework with adaptive global-local guidance, which substantially outperforms strong baselines in experiments across two challenging benchmarks.
Large language model (LLM)-based agents have demonstrated remarkable capabilities in decision-making tasks, but struggle significantly with complex, long-horizon planning scenarios. This arises from their lack of macroscopic guidance, causing disorientation and failures in complex tasks, as well as insufficient continuous oversight during execution, rendering them unresponsive to environmental changes and prone to deviations. To tackle these challenges, we introduce HiPlan, a hierarchical planning framework that provides adaptive global-local guidance to boost LLM-based agents'decision-making. HiPlan decomposes complex tasks into milestone action guides for general direction and step-wise hints for detailed actions. During the offline phase, we construct a milestone library from expert demonstrations, enabling structured experience reuse by retrieving semantically similar tasks and milestones. In the execution phase, trajectory segments from past milestones are dynamically adapted to generate step-wise hints that align current observations with the milestone objectives, bridging gaps and correcting deviations. Extensive experiments across two challenging benchmarks demonstrate that HiPlan substantially outperforms strong baselines, and ablation studies validate the complementary benefits of its hierarchical components.