@inproceedings{rao-etal-2026-utp,
title = "{UTP}-Bench: Uncertainty-aware Travel Planning Benchmark",
author = "Rao, Etcharla Revanth and
Karmakar, Priyanshu and
Mallick, Shubhojit and
Gupta, Manish and
Ghosh, Shreya and
Jana, Abhik",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2065/",
pages = "43945--43978",
ISBN = "979-8-89176-462-0",
abstract = "Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real-world travel planning is inherently uncertain: transportation delays, crowd fluctuations, and unexpected stochastic delays frequently invalidate otherwise feasible schedules. Existing benchmarks like TravelPlanner and TripCraft assume deterministic environments, evaluating only static constraint satisfaction and ignoring whether generated plans remain robust when such uncertainties arise.\par To address this limitation, we introduce UTP-Bench, a large-scale benchmark for uncertainty-aware travel planning. The dataset integrates real-world travel data spanning 504 cities of India, including attractions, restaurants, accommodations, and multi-modal transportation networks. To model realistic disruptions, UTP-Bench incorporates empirical delay distributions and crowd-density patterns collected from major cities, enabling evaluation of travel plans under stochastic conditions.\par We further propose three evaluation metrics, namely Buffer Adequacy Score (BAS), Crowd-Aware Timing Score (CATS), and Transport Delay Absorption Score (TDAS), which quantify the ability of generated itineraries to maintain robustness against transit delays and crowd variability. Experiments with state-of-the-art LLMs like GPT-5, Qwen3, Mistral and Phi-4 reveal substantial gaps between model-generated and human-authored plans, particularly in temporal buffering, delay-aware transportation scheduling, and crowd-sensitive planning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rao-etal-2026-utp">
<titleInfo>
<title>UTP-Bench: Uncertainty-aware Travel Planning Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Etcharla</namePart>
<namePart type="given">Revanth</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanshu</namePart>
<namePart type="family">Karmakar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubhojit</namePart>
<namePart type="family">Mallick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shreya</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhik</namePart>
<namePart type="family">Jana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real-world travel planning is inherently uncertain: transportation delays, crowd fluctuations, and unexpected stochastic delays frequently invalidate otherwise feasible schedules. Existing benchmarks like TravelPlanner and TripCraft assume deterministic environments, evaluating only static constraint satisfaction and ignoring whether generated plans remain robust when such uncertainties arise.\par To address this limitation, we introduce UTP-Bench, a large-scale benchmark for uncertainty-aware travel planning. The dataset integrates real-world travel data spanning 504 cities of India, including attractions, restaurants, accommodations, and multi-modal transportation networks. To model realistic disruptions, UTP-Bench incorporates empirical delay distributions and crowd-density patterns collected from major cities, enabling evaluation of travel plans under stochastic conditions.\par We further propose three evaluation metrics, namely Buffer Adequacy Score (BAS), Crowd-Aware Timing Score (CATS), and Transport Delay Absorption Score (TDAS), which quantify the ability of generated itineraries to maintain robustness against transit delays and crowd variability. Experiments with state-of-the-art LLMs like GPT-5, Qwen3, Mistral and Phi-4 reveal substantial gaps between model-generated and human-authored plans, particularly in temporal buffering, delay-aware transportation scheduling, and crowd-sensitive planning.</abstract>
<identifier type="citekey">rao-etal-2026-utp</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2065/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>43945</start>
<end>43978</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UTP-Bench: Uncertainty-aware Travel Planning Benchmark
%A Rao, Etcharla Revanth
%A Karmakar, Priyanshu
%A Mallick, Shubhojit
%A Gupta, Manish
%A Ghosh, Shreya
%A Jana, Abhik
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F rao-etal-2026-utp
%X Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real-world travel planning is inherently uncertain: transportation delays, crowd fluctuations, and unexpected stochastic delays frequently invalidate otherwise feasible schedules. Existing benchmarks like TravelPlanner and TripCraft assume deterministic environments, evaluating only static constraint satisfaction and ignoring whether generated plans remain robust when such uncertainties arise.\par To address this limitation, we introduce UTP-Bench, a large-scale benchmark for uncertainty-aware travel planning. The dataset integrates real-world travel data spanning 504 cities of India, including attractions, restaurants, accommodations, and multi-modal transportation networks. To model realistic disruptions, UTP-Bench incorporates empirical delay distributions and crowd-density patterns collected from major cities, enabling evaluation of travel plans under stochastic conditions.\par We further propose three evaluation metrics, namely Buffer Adequacy Score (BAS), Crowd-Aware Timing Score (CATS), and Transport Delay Absorption Score (TDAS), which quantify the ability of generated itineraries to maintain robustness against transit delays and crowd variability. Experiments with state-of-the-art LLMs like GPT-5, Qwen3, Mistral and Phi-4 reveal substantial gaps between model-generated and human-authored plans, particularly in temporal buffering, delay-aware transportation scheduling, and crowd-sensitive planning.
%U https://aclanthology.org/2026.findings-emnlp.2065/
%P 43945-43978
Markdown (Informal)
[UTP-Bench: Uncertainty-aware Travel Planning Benchmark](https://aclanthology.org/2026.findings-emnlp.2065/) (Rao et al., Findings 2026)
ACL
- Etcharla Revanth Rao, Priyanshu Karmakar, Shubhojit Mallick, Manish Gupta, Shreya Ghosh, and Abhik Jana. 2026. UTP-Bench: Uncertainty-aware Travel Planning Benchmark. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 43945–43978, Budapest, Hungary. Association for Computational Linguistics.