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

Carnegie Mellon study suggests showing concrete options helps planning agents find acceptable plansMachine translation

AI introduction

A post describing a Carnegie Mellon paper says people planning trips or shopping may accept trade-offs outside their stated limits once they see concrete options. It reports that adding one unstated trade-off to a request raised the share of plans users accepted from 12% to 55% with the same planner; the paper’s experimental conditions still need checking.

Original post · Original

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

@rohanpaul_ai

– https://t.co/fNh4JUOMue

Title: "How Should Planning Agents ReSHAPE Their Search Space?"

ReplyRohan Paul@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.
View this post on X ↗

Source: Rohan Paul · x.com

Research
Found an error? Send a correction