Tag
This paper investigates numerical Totally-Ordered HTN planning by extending SAT-based encodings with SMT to handle numeric fluents, introduces a benchmark suite, and shows competitive performance as a baseline for future work.
The paper presents a temporal planning framework for intelligent flood response, enabling coordinated scheduling and dynamic replanning under resource constraints.
Git-Assistant is an AI-powered tool that combines large language models with automated planning to help developers execute complex git operations more safely and reliably.
This paper presents a complementary evaluation of PlanGPT, a large language model for automated planning, using plan cost and plan generation time metrics, and finds that PlanGPT performs no better than a greedy search strategy.