Search papers, labs, and topics across Lattice.
The paper introduces Behavior Forest, a novel travel planning method that decomposes the decision-making process into parallel behavior trees, each responsible for a subtask, to address the challenges of multi-constraint planning. A global coordination mechanism orchestrates interactions among these trees, enabling modular and coherent planning. Experiments on TravelPlanner and ChinaTravel benchmarks demonstrate that Behavior Forest outperforms state-of-the-art methods by 6.67% and 11.82%, respectively, showcasing its effectiveness in enhancing LLM performance for complex travel planning.
LLMs can plan complex trips far more effectively when their reasoning is structured as a "forest" of parallel behavior trees, each handling a subtask and coordinated globally.
Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In such tasks, each planning step is not only constrained locally but also influenced by global constraints spanning multiple subtasks, leading to a tightly coupled and complex decision process. Existing travel planning methods typically rely on a single decision space that entangles all subtasks and constraints, failing to distinguish between locally acting constraints within a subtask and global constraints that span multiple subtasks. Consequently, the model is forced to jointly reason over local and global constraints at each decision step, increasing the reasoning burden and reducing planning efficiency. To address this problem, we propose the Behavior Forest method. Specifically, our approach structures the decision-making process into a forest of parallel behavior trees, where each behavior tree is responsible for a subtask. A global coordination mechanism is introduced to orchestrate the interactions among these trees, enabling modular and coherent travel planning. Within this framework, large language models are embedded as decision engines within behavior tree nodes, performing localized reasoning conditioned on task-specific constraints to generate candidate subplans and adapt decisions based on coordination feedback. The behavior trees, in turn, provide an explicit control structure that guides LLM generation. This design decouples complex tasks and constraints into manageable subspaces, enabling task-specific reasoning and reducing the cognitive load of LLM. Experimental results show that our method outperforms state-of-the-art methods by 6.67% on the TravelPlanner and by 11.82% on the ChinaTravel benchmarks, demonstrating its effectiveness in increasing LLM performance for complex multi-constraint travel planning.