Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.11271 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908707161374720 |
|---|---|
| author | Chen, Yuxing Suleiman, Basem Chen, Qifan |
| author_facet | Chen, Yuxing Suleiman, Basem Chen, Qifan |
| contents | Real-world trip planning requires transforming open-ended user requests into executable itineraries under strict spatial, temporal, and budgetary constraints while aligning with user preferences. Existing LLM-based agents struggle with constraint satisfaction, tool coordination, and efficiency, often producing infeasible or costly plans. To address these limitations, we present TriFlow, a progressive multi-agent framework that unifies structured reasoning and language-based flexibility through a three-stage pipeline of retrieval, planning, and governance. By this design, TriFlow progressively narrows the search space, assembles constraint-consistent itineraries via rule-LLM collaboration, and performs bounded iterative refinement to ensure global feasibility and personalisation. Evaluations on TravelPlanner and TripTailor benchmarks demonstrated state-of-the-art results, achieving 91.1% and 97% final pass rates, respectively, with over 10x runtime efficiency improvement compared to current SOTA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11271 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TriFlow: A Progressive Multi-Agent Framework for Intelligent Trip Planning Chen, Yuxing Suleiman, Basem Chen, Qifan Artificial Intelligence Real-world trip planning requires transforming open-ended user requests into executable itineraries under strict spatial, temporal, and budgetary constraints while aligning with user preferences. Existing LLM-based agents struggle with constraint satisfaction, tool coordination, and efficiency, often producing infeasible or costly plans. To address these limitations, we present TriFlow, a progressive multi-agent framework that unifies structured reasoning and language-based flexibility through a three-stage pipeline of retrieval, planning, and governance. By this design, TriFlow progressively narrows the search space, assembles constraint-consistent itineraries via rule-LLM collaboration, and performs bounded iterative refinement to ensure global feasibility and personalisation. Evaluations on TravelPlanner and TripTailor benchmarks demonstrated state-of-the-art results, achieving 91.1% and 97% final pass rates, respectively, with over 10x runtime efficiency improvement compared to current SOTA. |
| title | TriFlow: A Progressive Multi-Agent Framework for Intelligent Trip Planning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.11271 |