Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2506.02683 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912411320057856 |
|---|---|
| author | Lu, Zhengdong Lu, Weikai Tao, Yiling Dai, Yun Chen, ZiXuan Zhuang, Huiping Chen, Cen Peng, Hao Zeng, Ziqian |
| author_facet | Lu, Zhengdong Lu, Weikai Tao, Yiling Dai, Yun Chen, ZiXuan Zhuang, Huiping Chen, Cen Peng, Hao Zeng, Ziqian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02683 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints Lu, Zhengdong Lu, Weikai Tao, Yiling Dai, Yun Chen, ZiXuan Zhuang, Huiping Chen, Cen Peng, Hao Zeng, Ziqian Computation and Language 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. |
| title | Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.02683 |