AI/ ai · llm-research · benchmarks · travel-tech

Study Finds Fine-Tuning Outperforms Prompting for AI Trip Planners

A new benchmark built from real user logs and expert judgments finds that fine-tuned models plan trips better than prompted ones, at similar speed.

A new benchmark says fine-tuning a language model still beats clever prompting when the task is planning someone's vacation.

Researchers built TripScore, a benchmark drawn from real user logs and calibrated against 1,468 pairwise judgments from 203 travel experts, because most people typing into a trip-planning bot give vague requests rather than neat checklists of constraints. The benchmark pairs a feasibility check for format and basic sense with a single reward score that blends output quality and how well a plan matches what the traveler actually wanted. The team then tested several approaches under the same base model and comparable response times: direct prompting, giving the model more "thinking" time, symbolic solvers bolted onto the LLM, code-writing agents, and reinforcement-learning fine-tuning such as GRPO. Fine-tuning won consistently across the comparison.

For consumer AI products, that is a data point against the assumption that a good enough prompt can substitute for retraining. It suggests that companies shipping travel bots, or any tool that has to handle messy, constraint-heavy requests from real users, may need to budget for fine-tuning pipelines rather than leaning entirely on prompt engineering.

One caveat: the result comes from the same team's own benchmark, calibrated on their own service's users - promising, but worth reproducing on other tasks before anyone rewrites their AI roadmap around it.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →