Back to AI News
arxiv

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.

AI Brief

Provides concrete evidence and a new benchmark for a practical improvement in interactive planning agents.

arXiv:2611.16466v1 Announce Type: new Abstract: Planning agents and benchmarks treat a user's initial specification as fixed. Yet the requests users write exclude plans they would gladly take, since they rarely discover the possible trade-offs they would accept until seeing the options. Agents already revise requests through interaction, but whether this helps planning is unknown. We formalize this step as the ReSHAPE task, which judges a revision by whether its search space matches the acceptable plans and a planner finds one there. Using ReSHAPE Planter, which builds instances from planning benchmarks with a human-validated simulated user, we analyze 5,800 agent-revised specifications in travel and shopping. We find that reshaping matters: one correct trade-off makes the same planner reach an acceptable plan up to 4.6x as often, and search space quality predicts what the planner finds. Current agents, however, admit at most 32% of the acceptable plans, where that trade-off alone admits over 52%, because they ask about preferences instead of showing plans; in travel, showing plans raises F1 by 9.7 points over asking, with two model families. Planning agents should thus treat a request as a hypothesis to test against the user's reactions to concrete plans to recognize user trade-offs.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!