We introduce a novel framework for evaluating the alignment between natural language plans and their expected behavior by converting them into Kripke structures and Linear Temporal Logic (LTL) using Large Language Models (LLMs) and performing model checking. We systematically evaluate this framework on a simplified version of the PlanBench plan verification dataset and report on metrics like Accuracy, Precision, Recall and F1 scores. Our experiments demonstrate that GPT-5 achieves excellent classification performance (F1 score of 96.3%) while almost always producing syntactically perfect formal representations that can act as guarantees. However, the synthesis of semantically perfect formal models remains an area for future exploration.

Multi-agent Epistemic Planning (MEP) is an autonomous planning framework for reasoning about both the physical world and the beliefs of agents, with applications in domains where information flow and awareness among agents are critical. The richness of MEP requires states to be represented as Kripke structures, i.e., directed labeled graphs. This representation limits the applicability of existing heuristics, hindering the scalability of epistemic solvers, which must explore an exponential search space without guidance, resulting often in intractability. To address this, we exploit Graph Neural Networks (GNNs) to learn patterns and relational structures within epistemic states, to guide the planning process. GNNs, which naturally capture the graph-like nature of Kripke models, allow us to derive meaningful estimates of state quality -- e.g., the distance from the nearest goal -- by generalizing knowledge obtained from previously solved planning instances. We integrate these predictive heuristics into an epistemic planning pipeline and evaluate them against standard baselines, showing improvements in the scalability of multi-agent epistemic planning.

In this paper, we present a conceptual model game to examine the dynamics of asymmetric interactions in games with imperfect information. The game involves two agents with starkly contrasting capabilities: one agent can take actions but has no information of the state of the game, whereas the other agent has perfect information of the state but cannot act or observe the other agent's actions. This duality manifests an extreme form of asymmetry, and how differing abilities influence the possibility of attaining common knowledge. Using Kripke structures and epistemic logic we demonstrate that, under these conditions, common knowledge of the current game state becomes unattainable. Our findings advance the discussion on the strategic limitations of knowledge in environments where information and action are unevenly distributed.

Multimodal foundation models offer a promising framework for robotic perception and planning by processing sensory inputs to generate actionable plans. However, addressing uncertainty in both perception (sensory interpretation) and decision-making (plan generation) remains a critical challenge for ensuring task reliability. We present a comprehensive framework to disentangle, quantify, and mitigate these two forms of uncertainty. We first introduce a framework for uncertainty disentanglement, isolating perception uncertainty arising from limitations in visual understanding and decision uncertainty relating to the robustness of generated plans. To quantify each type of uncertainty, we propose methods tailored to the unique properties of perception and decision-making: we use conformal prediction to calibrate perception uncertainty and introduce Formal-Methods-Driven Prediction (FMDP) to quantify decision uncertainty, leveraging formal verification techniques for theoretical guarantees. Building on this quantification, we implement two targeted intervention mechanisms: an active sensing process that dynamically re-observes high-uncertainty scenes to enhance visual input quality and an automated refinement procedure that fine-tunes the model on high-certainty data, improving its capability to meet task specifications. Empirical validation in real-world and simulated robotic tasks demonstrates that our uncertainty disentanglement framework reduces variability by up to 40% and enhances task success rates by 5% compared to baselines. These improvements are attributed to the combined effect of both interventions and highlight the importance of uncertainty disentanglement which facilitates targeted interventions that enhance the robustness and reliability of autonomous systems.

The new field of Explainable Planning (XAIP) has produced a variety of approaches to explain and describe the behavior of autonomous agents to human observers. Many summarize agent behavior in terms of the constraints, or ''rules,'' which the agent adheres to during its trajectories. In this work, we narrow the focus from summary to specific moments in individual trajectories, offering a ''pointwise-in-time'' view. Our novel framework, which we define on Linear Temporal Logic (LTL) rules, assigns an intuitive status to any rule in order to describe the trajectory progress at individual time steps; here, a rule is classified as active, satisfied, inactive, or violated. Given a trajectory, a user may query for status of specific LTL rules at individual trajectory time steps. In this paper, we present this novel framework, named Rule Status Assessment (RSA), and provide an example of its implementation. We find that pointwise-in-time status assessment is useful as a post-hoc diagnostic, enabling a user to systematically track the agent's behavior with respect to a set of rules.

Owing to their remarkable learning capabilities and performance in real-world applications, the use of machine learning systems based on Neural Networks (NNs) has been continuously increasing. However, various case studies and empirical findings in the literature suggest that slight variations to NN inputs can lead to erroneous and undesirable NN behavior. This has led to considerable interest in their formal analysis, aiming to provide guarantees regarding a given NN's behavior. Existing frameworks provide robustness and/or safety guarantees for the trained NNs, using satisfiability solving and linear programming. We proposed FANNet, the first model checking-based framework for analyzing a broader range of NN properties. However, the state-space explosion associated with model checking entails a scalability problem, making the FANNet applicable only to small NNs. This work develops state-space reduction and input segmentation approaches, to improve the scalability and timing efficiency of formal NN analysis. Compared to the state-of-the-art FANNet, this enables our new model checking-based framework to reduce the verification's timing overhead by a factor of up to 8000, making the framework applicable to NNs even with approximately $80$ times more network parameters. This in turn allows the analysis of NN safety properties using the new framework, in addition to all the NN properties already included with FANNet. The framework is shown to be efficiently able to analyze properties of NNs trained on healthcare datasets as well as the well--acknowledged ACAS Xu NNs.

We introduce CPDL+, a family of expressive logics rooted in Propositional Dynamic Logic (PDL). In terms of expressive power, CPDL+ strictly contains PDL extended with intersection and converse (a.k.a. ICPDL) as well as Conjunctive Queries (CQ), Conjunctive Regular Path Queries (CRPQ), or some known extensions thereof (Regular Queries and CQPDL). We investigate the expressive power, characterization of bisimulation, satisfiability, and model checking for CPDL+. We argue that natural subclasses of CPDL+ can be defined in terms of the tree-width of the underlying graphs of the formulas. We show that the class of CPDL+ formulas of tree-width 2 is equivalent to ICPDL, and that it also coincides with CPDL+ formulas of tree-width 1. However, beyond tree-width 2, incrementing the tree-width strictly increases the expressive power. We characterize the expressive power for every class of fixed tree-width formulas in terms of a bisimulation game with pebbles. Based on this characterization, we show that CPDL+ has a tree-like model property. We prove that the satisfiability problem is decidable in 2ExpTime on fixed tree-width formulas, coinciding with the complexity of ICPDL. We also exhibit classes for which satisfiability is reduced to ExpTime. Finally, we establish that the model checking problem for fixed tree-width formulas is in \ptime, contrary to the full class CPDL+.

A highly autonomous system (HAS) has to assess the situation it is in and derive beliefs, based on which, it decides what to do next. The beliefs are not solely based on the observations the HAS has made so far, but also on general insights about the world, in which the HAS operates. These insights have either been built in the HAS during design or are provided by trusted sources during its mission. Although its beliefs may be imprecise and might bear flaws, the HAS will have to extrapolate the possible futures in order to evaluate the consequences of its actions and then take its decisions autonomously. In this paper, we formalize an autonomous decisive system as a system that always chooses actions that it currently believes are the best. We show that it can be checked whether an autonomous decisive system can be built given an application domain, the dynamically changing knowledge base and a list of LTL mission goals. We moreover can synthesize a belief formation for an autonomous decisive system. For the formal characterization, we use a doxastic framework for safety-critical HASs where the belief formation supports the HAS's extrapolation.

Over the last few years, the concept of Artificial Intelligence has become central in different tasks concerning both our daily life and several working scenarios. Among these tasks automated planning has always been central in the AI research community. In particular, this manuscript is focused on a specialized kind of planning known as Multi-agent Epistemic Planning (MEP). Epistemic Planning (EP) refers to an automated planning setting where the agent reasons in the space of knowledge/beliefs states and tries to find a plan to reach a desirable state from a starting one. Its general form, the MEP problem, involves multiple agents who need to reason about both the state of the world and the information flows between agents. To tackle the MEP problem several tools have been developed and, while the diversity of approaches has led to a deeper understanding of the problem space, each proposed tool lacks some abilities and does not allow for a comprehensive investigation of the information flows. That is why, the objective of our work is to formalize an environment where a complete characterization of the agents' knowledge/beliefs interaction and update is possible. In particular, we aim to achieve such goal by defining a new action-based language for multi-agent epistemic planning and to implement an epistemic planner based on it. This solver should provide a tool flexible enough to reason on different domains, e.g., economy, security, justice and politics, where considering others' knowledge/beliefs could lead to winning strategies.

An epistemic model for decentralized discrete-event systems with non-binary control is presented. This framework combines existing work on conditional control decisions with existing work on formal reasoning about knowledge in discrete-event systems. The novelty in the model presented is that the necessary and sufficient conditions for problem solvability encapsulate the actions that supervisors must take. This direct coupling between knowledge and action -- in a formalism that mimics natural language -- makes it easier, when the problem conditions fail, to determine how the problem requirements should be revised.