TREK Benchmark

What is TREK?

TREK evaluates agents on synthesizing feasible travel itineraries under interacting entity, route, time, budget, and persona constraints.

Released

2026-07-29

Evaluates

General AI, Language & Knowledge, Planning, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.26977

TREK paper and code

• Paper https://arxiv.org/abs/2607.26977
• Code https://github.com/TonyQJH/TREK-A-Travel-Reasoning-and-Evaluation-Kit-for-LLM-Agents-in-Complex-Trip-Planning

Which sources cite TREK?

• TREK

Related General AI, Language & Knowledge, Planning, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ABC-Bench