The paper "Lose the Order, Keep the Hierarchy: Deordering HTN Plans" adapts two classical plan deordering techniques to the Hierarchical Task Network (HTN) planning framework, extending them to respect hierarchical decomposition constraints. The authors evaluate their methods on the IPC 2023 Partial-Order HTN benchmarks and compare them with Optiplan, an HTN planner that generates partially ordered plans directly. Results show a substantial reduction in ordering constraints, with a smaller but noticeable decrease in critical path length.
The paper introduces a method for numerical Totally-Ordered HTN (TOHTN) planning by extending standard SAT-based encodings with SMT to handle numeric fluents. It also presents a new benchmark suite for evaluating numerical TOHTN planning, providing a common basis for future research. Experimental results demonstrate that this straightforward encoding serves as a competitive baseline for the field.
The paper evaluates strategies for increasing plan‑execution flexibility by converting sequential plans into partial‑order plans through deordering and reordering. It compares block deordering methods, which restructure causal dependencies, with MaxSAT‑based approaches that optimize within existing causal structures. The study finds that block deordering consistently outperforms MaxSAT in both effectiveness and efficiency, offering anytime solutions and higher flexibility gains per computation time.
arXiv:2607. 25484v1 Announce Type: new Abstract: In some real applications a plan may later become unfeasible due to newly imposed budget constraints, yet, at the same time, using only the original actions of the plan and their order is mandatory.
arXiv:2606. 06300v1 Announce Type: new Abstract: We propose MResOpt, a staged residual neural network architecture for constrained optimization problems.
arXiv:2603.08814v2 Announce Type: replace-cross Abstract: Long-horizon task planning for heterogeneous multi-robot systems is essential for deploying collaborative teams in real-world environments; y...
arXiv:2607. 17973v1 Announce Type: new Abstract: Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences.
arXiv:2609.38108v1 Announce Type: new Abstract: Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successfu...
arXiv:2607. 12547v1 Announce Type: cross Abstract: We investigate whether temporal hierarchy can improve LeWorldModel on long-horizon goal-conditioned control.
HorizonFlow is a hierarchical planner for offline goal-conditioned reinforcement learning that treats the planning horizon as an output rather than a fixed input. It uses a subgoal route planner and an action-prefix controller, both employing insertion-based generation and flow matching, to jointly generate continuous plan content and its length. The method leverages the partially generated plan to guide token insertion and to steer generation toward shorter plans, achieving superior performance on Maze2D, Multi2D, and OGBench benchmarks.
Recent advances in generative planning have made trajectory inpainting a promising approach to offline goal-conditioned reinforcement learning. However, these methods typically specify the planning ho...
PIE-APT introduces a unified framework for abductive planning over Temporal Dynamic Knowledge Graphs (TDKGs) using two modules: PIE-Abducer, which performs incremental direct-derivation abduction, and PIE-APT, which interleaves backward‑chaining A* search with PIE-Abducer to generate action sequences and abductive assumptions. The approach operates natively on the expressive SROIQ Description Logic, leveraging an incremental reasoner to maintain decidability and bypass the Ramification Problem. Evaluation on four OWL benchmarks demonstrates qualitative superiority over classical planners and shows that the direct‑derivation method outperforms a Minimal Hitting Set baseline in abductive enrichment.
arXiv:2501. 18784v5 Announce Type: replace Abstract: Heuristics are a central component of deterministic planning, particularly in domain-independent settings where general applicability is prioritized over task-specific tuning.