aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score54

Carnegie Mellon paper: Showing concrete choices helps shopping and travel assistants find more acceptable options than asking preferencesMachine translation

AI introduction

The research says users may not state in advance that they would accept a lower rating for a lower price, but may make that trade-off when they see actual options. With the same planner, adding one hidden trade-off to a request raised the share of plans accepted from 12% to 55%. The source also says current agents that mostly asked questions found at most 32% of plans users would accept.

Original post · Original

The article text is unavailable in this language; an existing version is shown.

@rohanpaul_ai

New Carnegie Mellon paper finds that AI assistants that plan trips and shopping find more options people would accept by showing them a few real choices than by asking about their preferences.

A travel request like “restaurants rated 3.8 or higher” throws out a cheaper place rated 3.7 that the user would happily pick. People rarely say they would accept a lower rating to save money, because they only realize it when they see the actual options.

> Adding that 1 hidden trade-off to the request raised the share of plans the user accepted from 12% to 55%, with the same planner.

> Current agents (Claude Code, Gemini CLI and others) mostly asked questions and rarely showed plans, so they caught at most 32% of plans the user would accept.

> Agents that showed plans did clearly better than agents that asked.

When your agent turns a request into a plan, show the user a few options outside their stated limits early, before locking the spec.

Source: Rohan Paul · x.com

Research
Found an error? Send a correction