Planning Agents Should Reshape Search Space by Showing Plans, Not Asking Preferences
This paper introduces ReSHAPE, a task for evaluating whether an agent's revision of a user's initial specification improves planning by better matching acceptable plans. Using ReSHAPE Planter with human-validated simulated users, the authors analyze 5,800 agent-revised specifications in travel and shopping. They find that a single correct trade-off can make the same planner reach an acceptable plan up to 4.6x as often, while current agents admit at most 32% of acceptable plans. Showing concrete plans instead of asking about preferences raises F1 by 9.7 points in travel across two model families.