Skip to content
Conference Open access

Platform-Aware Mission Planning with Task-Level Contracts

Sep 2026 · Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence · pp. 6191-6198 · 0 citations · 23 references

TL;DR

A framework to exploit task-level contracts, expressed as assumptions and guarantees at the beginning and end of tasks, to automatically synthesize plans that are guaranteed to be correct on any system satisfying the contracts is proposed.

Abstract

Automated temporal planning is used to synthesize courses of action for a deterministic abstraction of a system; the produced plans are often modeled as schedules of tasks to be executed on the real system under control. A key problem with adopting this architecture is how to ensure the plan is executable and goal-reaching on the real system, which can be arbitrarily complex and possibly non-deterministic. In this paper, we propose a framework to exploit task-level contracts, expressed as assumptions and guarantees at the beginning and end of tasks, to automatically synthesize plans that are guaranteed to be correct on any system satisfying the contracts. Our framework combines a temporal planner to generate candidate plans and a contract reasoner to instantiate and verify the contracts associated with the plan. If the plan is found invalid, we refine the planning problem until a valid plan is found. We present an experimental evaluation on a realistic case-study and on several synthetic problems, showing the applicability of the approach.

Read PDF

Similar papers

#artificial intelligence Preprint Sep 2026

Provably Complete Generalized Planning with LLMs

This work introduces a semantic-preserving PDDL-to-Lean conversion, and uses an LLM to generate both the generalized plan and the formal proof that it solves every instance satisfying the domain constraints, and evaluates this approach on 13 commonly used benchmark domains.

Katharina Stein, Chaahat Jain, J. Hoffmann et al. · 0 citations

Proper Open World Automated Planning

It is shown a proof-of-the-concept lifted planner can sometimes solve the BPP problem by using a domain-independent heuristic that guides search for a plan.

Mikhail Soutchanski · 0 citations

Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution

The Plan Declaration--Execution Gap is studied and Planning-as-Routing is introduced, where an LLM declares one of four planning modes: Predefined, Sequential, Hierarchical, or Search and a deterministic router dispatches the task to the corresponding pattern-specific executor.

S. Oota, Francisco Herrera, Jordi Cabot Sagrera et al. · 1 citation
Preprint Sep 2026

Conditional Timed Partial Orders: An Expressive and Interpretable Framework for Robot Task Specification and Planning

This paper introduces Conditional TPOs (cTPOs), which extend TPOs with richer relative-timing constraints and conditional event activations based on environmental conditions and proves that this decomposition is complete and preserves plan optimality while improving the interpretability of complex tasks.

Sebastián Escobar, Morteza Lahijanian · 0 citations

Consistent Plan-Act for Long-Horizon Agentic Tasks

Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning from low-level execution through separate planner and actor roles. To investigate coordination failures in these tasks, we prompt both agen...

Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang et al. · 1 citation
#artificial intelligence Preprint Sep 2026

Planning and Scheduling Business Processes under Control-Flow Uncertainty: Extended Version

A decomposed approach with two stages, a planning stage that minimizes the expected number of superfluous activities subject to a feasibility constraint, and a scheduling stage that minimizes the makespan over the planned activities; and an integrated approach that combines planning and scheduling into a single formula...

Michel Kunkler, Stefanie Rinderle-Ma · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.