Bookmark Saya

arXiv Open Access 2025

Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints

Zhengdong Lu Weikai Lu Yiling Tao Yun Dai ZiXuan Chen +4 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CL

Penulis (9)

Z

Zhengdong Lu

W

Weikai Lu

Y

Yiling Tao

Y

Yun Dai

Z

ZiXuan Chen

H

Huiping Zhuang

C

Cen Chen

H

Hao Peng

Z

Ziqian Zeng

Format Sitasi

APA MLA BibTeX
Lu, Z., Lu, W., Tao, Y., Dai, Y., Chen, Z., Zhuang, H. et al. (2025). Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints. https://arxiv.org/abs/2506.02683

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓