# Revisiting the Travel Planning Capabilities of Large Language Models

arXiv: https://arxiv.org/abs/2605.03308 · HTML: https://mlsanity.com/paper/2605.03308/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [Memp: Exploring Agent Procedural Memory](https://mlsanity.com/paper/2508.06433/) (2025)
- [DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents](https://mlsanity.com/paper/2406.06769/) (2024)
- [Agent Learning via Early Experience](https://mlsanity.com/paper/2510.08558/) (2025)
- [LLM With Tools: A Survey](https://mlsanity.com/paper/2409.18807/) (2024)
- [Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools](https://mlsanity.com/paper/2404.11891/) (2024)
- [Planning with Multi-Constraints via Collaborative Language Agents](https://mlsanity.com/paper/2405.16510/) (2024)
- [TripTailor: A Real-World Benchmark for Personalized Travel Planning](https://mlsanity.com/paper/2508.01432/) (2025)
- [To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning](https://mlsanity.com/paper/2410.16456/) (2024)
- [TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planning](https://mlsanity.com/paper/2502.20508/) (2025)
- [DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents](https://mlsanity.com/paper/2509.21842/) (2025)
- [Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface](https://mlsanity.com/paper/2410.00079/) (2024)
- [ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents](https://mlsanity.com/paper/2412.13682/) (2024)
- [LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents](https://mlsanity.com/paper/2505.22634/) (2025)
- [ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning](https://mlsanity.com/paper/2509.25586/) (2025)
- [A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models](https://mlsanity.com/paper/2405.18208/) (2024)
- [RETAIL: Towards Real-world Travel Planning for Large Language Models](https://mlsanity.com/paper/2508.15335/) (2025)
- [TripTide: A Benchmark for Adaptive Travel Planning under Disruptions](https://mlsanity.com/paper/2510.21329/) (2025)
- [Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints](https://mlsanity.com/paper/2506.02683/) (2025)

## Abstract (arXiv)

Travel planning serves as a critical task for long-horizon reasoning, exposing significant deficits in LLMs. However, existing benchmarks and evaluations primarily assess final plans in an end-to-end manner, which lacks interpretability and makes it difficult to analyze the root causes of failures. To bridge this gap, we decompose travel planning into five constituent atomic sub-capabilities, including Constraint Extraction, Tool Use, Plan Generation, Error Identification, and Error Correction. We implement a decoupled evaluation protocol leveraging oracle intermediate contexts to rigorously isolate these components, thereby measuring the atomic performance boundary without the noise of cascading errors. Our results highlight a clear contrast in performance: while LLMs are proficient in extracting explicit constraints, they struggle to infer implicit, open-world requirements. Furthermore, they exhibit structural biases in plan generation and suffer from ineffective self-correction, characterized by excessive sensitivity and erroneous persistence. These findings offer precise directions for improving LLM reasoning and planning abilities.