发表机构
TU Darmstadt; TU Munich（达姆施塔特工业大学; 慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有流程规划方法缺乏任务逻辑约束的问题，提出CEFITO方法，将流程规划构建为任务约束优化问题，在两个基准上取得最先进准确率。
AI 中文摘要
流程规划旨在估算一系列动作，以从观测到的初始状态过渡到给定的目标状态。当前的流程规划方法使用前馈神经网络或基于扩散的推理，从潜在表示直接预测动作序列。这些范式将每个动作视为可行的，缺乏执行特定任务逻辑约束的能力，而这些约束会使某些动作无关或不可行。我们提出CEFITO，一种流程规划方法，该方法学习一个预测器以表达动作条件化的表示空间。基于该表示空间，我们将流程规划构建为任务约束优化问题。与现有方法不同，CEFITO在推理时规划过程中通过省略无关动作，显式地对动作空间进行推理。这种重构实现了有效的流程规划，并在两个已建立的流程规划基准上达到了最先进的准确率。
英文摘要
Procedure planning seeks to estimate a sequence of actions to transition from an observed initial state to a given goal state. Current procedure planning approaches directly predict action sequences from latent representations using feed-forward neural networks or diffusion-based inference. These paradigms treat every action as plausible, lacking the ability to enforce task-specific logical constraints that render certain actions irrelevant or not plausible. We propose CEFITO, a procedure planning approach that learns a predictor to express an action-conditioned representation space. Based on this representation space, we formulate procedure planning as a task-constrained optimization problem. Unlike prior methods, CEFITO explicitly reasons over the action space by omitting irrelevant actions during inference-time planning. This reformulation enables effective procedure planning and achieves state-of-the-art accuracy on two established procedure planning benchmarks.
CommentsTo appear at GCPR 2026 (oral paper). Project page: https://visinf.github.io/cefito
