Princeton University users: to view a senior thesis while away from campus, connect to the campus network via the Global Protect virtual private network (VPN). Unaffiliated researchers: please note that requests for copies are handled manually by staff and require time to process.
 

Publication:

LLM Supervised ReAct Agents for Travel Planning

Simple item page
datacite.rightsrestricted
dc.contributor.advisorBangalore, Srinivas
dc.contributor.authorArnold, Christian T.
dc.date.accessioned2025-08-06T15:51:35Z
dc.date.available2025-08-06T15:51:35Z
dc.date.issued2025-04-10
dc.description.abstractConstraint driven travel planning, easy for humans, remains difficult for AI systems. We examine the TravelPlanner benchmark provided by Xie et al, and provide the new ManagerAgent architecture for travel planning. We find a preliminary 5% success rate across “Easy” queries, an improvement from 0% success rates reported from other models and frameworks. This thesis details the ManagerAgent for travel planning, providing an in-depth implementation description. Code is available at github.com/ctarnold/TravelPlanner.
dc.identifier.urihttps://theses-dissertations.princeton.edu/handle/88435/dsp01ns064948t
dc.language.isoen_US
dc.titleLLM Supervised ReAct Agents for Travel Planning
dc.typePrinceton University Senior Theses
dspace.entity.typePublication
dspace.workflow.startDateTime2025-04-10T21:29:55.063Z
pu.contributor.authorid920278415
pu.date.classyear2025
pu.departmentComputer Science

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
ca2992_written_final_report (1).pdf
Size:
522.54 KB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
100 B
Format:
Item-specific license agreed to upon submission
Description:
Download

Collections

Computer Science, 1987-2025