Score: 1

Flex-TravelPlanner: A Benchmark for Flexible Planning with Language Agents

Published: June 5, 2025 | arXiv ID: 2506.04649v1

By: Juhyun Oh, Eunsu Kim, Alice Oh

Potential Business Impact:

Tests if AI can change plans when things change.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Real-world planning problems require constant adaptation to changing requirements and balancing of competing constraints. However, current benchmarks for evaluating LLMs' planning capabilities primarily focus on static, single-turn scenarios. We introduce Flex-TravelPlanner, a benchmark that evaluates language models' ability to reason flexibly in dynamic planning scenarios. Building on the TravelPlanner dataset~\citep{xie2024travelplanner}, we introduce two novel evaluation settings: (1) sequential constraint introduction across multiple turns, and (2) scenarios with explicitly prioritized competing constraints. Our analysis of GPT-4o and Llama 3.1 70B reveals several key findings: models' performance on single-turn tasks poorly predicts their ability to adapt plans across multiple turns; constraint introduction order significantly affects performance; and models struggle with constraint prioritization, often incorrectly favoring newly introduced lower priority preferences over existing higher-priority constraints. These findings highlight the importance of evaluating LLMs in more realistic, dynamic planning scenarios and suggest specific directions for improving model performance on complex planning tasks. The code and dataset for our framework are publicly available at https://github.com/juhyunohh/FlexTravelBench.

Country of Origin
🇰🇷 Korea, Republic of

Repos / Data Links

Page Count
7 pages

Category
Computer Science:
Computation and Language