@inproceedings{karmakar-etal-2026-trippulse,
title = "{TRIPPULSE}: Multi-Agent Travel Planning with Review-Grounded Reasoning",
author = "Karmakar, Priyanshu and
Sai, Borru Vijay and
Mallick, Shubhojit and
Jana, Abhik and
Ghosh, Shreya and
Gupta, Manish",
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.2077/",
pages = "44223--44253",
ISBN = "979-8-89176-462-0",
abstract = "Travel itinerary generation requires balancing strict spatio-temporal constraints with human preferences. Existing LLM-based planners mainly rely on structured attributes and predefined traveler personas, but real travel decisions are often shaped by reviews that reveal experiential factors such as comfort, safety, service quality, ambiance, crowding, and hidden risks absent from structured databases. Incorporating such review information is therefore critical to realistic, user-centric itinerary generation. We propose TRIPPULSE (Captures experiential signals from reviews beyond rigid hard constraints), a multi-agent framework for review-grounded travel planning. Instead of relying on a monolithic planner (and face context and reasoning bottlenecks), TRIPPULSE decomposes itinerary generation into specialized agents (each operating over localized contexts) for accommodations, transportation, meals, attractions, and events, coordinated through a global orchestrator with scheduling mechanisms that enforce temporal and budget feasibility. We augment TripCraft with 100K+ real-world reviews and introduce Review-Grounded Persona Alignment (RGPA), an LLM-as-a-Judge metric for evaluating alignment with human-centric travel experiences. Experiments across multiple trip durations and diverse proprietary and open-source models show that TRIPPULSE maintains strong constraint satisfaction while generating more personalized and experientially grounded itineraries."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karmakar-etal-2026-trippulse">
<titleInfo>
<title>TRIPPULSE: Multi-Agent Travel Planning with Review-Grounded Reasoning</title>
</titleInfo>
<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">Borru</namePart>
<namePart type="given">Vijay</namePart>
<namePart type="family">Sai</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">Abhik</namePart>
<namePart type="family">Jana</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">Manish</namePart>
<namePart type="family">Gupta</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>Travel itinerary generation requires balancing strict spatio-temporal constraints with human preferences. Existing LLM-based planners mainly rely on structured attributes and predefined traveler personas, but real travel decisions are often shaped by reviews that reveal experiential factors such as comfort, safety, service quality, ambiance, crowding, and hidden risks absent from structured databases. Incorporating such review information is therefore critical to realistic, user-centric itinerary generation. We propose TRIPPULSE (Captures experiential signals from reviews beyond rigid hard constraints), a multi-agent framework for review-grounded travel planning. Instead of relying on a monolithic planner (and face context and reasoning bottlenecks), TRIPPULSE decomposes itinerary generation into specialized agents (each operating over localized contexts) for accommodations, transportation, meals, attractions, and events, coordinated through a global orchestrator with scheduling mechanisms that enforce temporal and budget feasibility. We augment TripCraft with 100K+ real-world reviews and introduce Review-Grounded Persona Alignment (RGPA), an LLM-as-a-Judge metric for evaluating alignment with human-centric travel experiences. Experiments across multiple trip durations and diverse proprietary and open-source models show that TRIPPULSE maintains strong constraint satisfaction while generating more personalized and experientially grounded itineraries.</abstract>
<identifier type="citekey">karmakar-etal-2026-trippulse</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2077/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>44223</start>
<end>44253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRIPPULSE: Multi-Agent Travel Planning with Review-Grounded Reasoning
%A Karmakar, Priyanshu
%A Sai, Borru Vijay
%A Mallick, Shubhojit
%A Jana, Abhik
%A Ghosh, Shreya
%A Gupta, Manish
%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 karmakar-etal-2026-trippulse
%X Travel itinerary generation requires balancing strict spatio-temporal constraints with human preferences. Existing LLM-based planners mainly rely on structured attributes and predefined traveler personas, but real travel decisions are often shaped by reviews that reveal experiential factors such as comfort, safety, service quality, ambiance, crowding, and hidden risks absent from structured databases. Incorporating such review information is therefore critical to realistic, user-centric itinerary generation. We propose TRIPPULSE (Captures experiential signals from reviews beyond rigid hard constraints), a multi-agent framework for review-grounded travel planning. Instead of relying on a monolithic planner (and face context and reasoning bottlenecks), TRIPPULSE decomposes itinerary generation into specialized agents (each operating over localized contexts) for accommodations, transportation, meals, attractions, and events, coordinated through a global orchestrator with scheduling mechanisms that enforce temporal and budget feasibility. We augment TripCraft with 100K+ real-world reviews and introduce Review-Grounded Persona Alignment (RGPA), an LLM-as-a-Judge metric for evaluating alignment with human-centric travel experiences. Experiments across multiple trip durations and diverse proprietary and open-source models show that TRIPPULSE maintains strong constraint satisfaction while generating more personalized and experientially grounded itineraries.
%U https://aclanthology.org/2026.findings-emnlp.2077/
%P 44223-44253
Markdown (Informal)
[TRIPPULSE: Multi-Agent Travel Planning with Review-Grounded Reasoning](https://aclanthology.org/2026.findings-emnlp.2077/) (Karmakar et al., Findings 2026)
ACL