规划智能体应如何重塑搜索空间？ReSHAPE 任务解析
How Should Planning Agents ReSHAPE Their Search Space?
AI 导读
一项 arXiv 研究提出 ReSHAPE 任务，评估规划智能体修订用户请求后搜索空间是否覆盖可接受方案。基于 ReSHAPE Planter 在旅行与购物场景分析 5,800 份修订规范，发现一个正确权衡能让同一规划器找到可接受方案的概率提升至 4.6 倍；但现有智能体最多只覆盖 32% 的可接受方案，直接展示方案而非询问偏好可将旅行场景 F1 提升 9.7 分。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.16466 [cs.AI] |
| (or arXiv:2611.16466v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16466 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yilin Zhang [view email]
[v1]
Thu, 12 Nov 2026 08:22:18 UTC (149 KB)
来源：arXiv cs.AI · arxiv.org