Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints
This addresses planning problems for LLM-based agents, offering a novel approach to handle multiple constraints, though it is incremental in improving existing planning methods.
The paper tackles the challenge of planning tasks with heavy constraints and cascading errors in Large Language Models (LLMs) by proposing DPPM, a novel parallel planning paradigm that decomposes tasks, plans subtasks in parallel, and merges subplans, which significantly outperforms existing methods in travel planning tasks.
Despite significant advances in Large Language Models (LLMs), planning tasks still present challenges for LLM-based agents. Existing planning methods face two key limitations: heavy constraints and cascading errors. To address these limitations, we propose a novel parallel planning paradigm, which Decomposes, Plans for subtasks in Parallel, and Merges subplans into a final plan (DPPM). Specifically, DPPM decomposes the complex task based on constraints into subtasks, generates the subplan for each subtask in parallel, and merges them into a global plan. In addition, our approach incorporates a verification and refinement module, enabling error correction and conflict resolution. Experimental results demonstrate that DPPM significantly outperforms existing methods in travel planning tasks.