arXiv subjects

Anne-Kathrin Schmuck

Publications and source records attributed to Anne-Kathrin Schmuck.

At least 19 recordsLinked to original sources

arXiv2026

Towards Actionable Strategy Certificates in Stochastic Parity Games

We propose a new approach for synthesizing large sets of winning strategies in stochastic parity games (2.5-player games) with quantitative objectives. Instead of computing a single, fully specified winning strategy, we introduce Actionable Strategy Certificates (ASCerts) as a local and permissive representation of a large class of system player winning strategies. To this end, we extend known certificates for stochastic invariants to the setting of games. Our certificates prove that synthesized strategies remain within a safe region of the game with probability at least $λ\in [0,1]$. As such, the certificates enhance the trustworthiness of synthesized strategies. The crux of our approach is to reinterpret and leverage the certificates as concise, local, and permissive representation of (possibly infinitely many) strategies. By carefully combining our certificates for stochastic invariants with strategy templates for almost-sure winning, we obtain a novel local representation of quantitatively winning strategies in stochastic parity games. This enables efficient synthesis, adaptation, and runtime strategy extraction, making ASCerts well suited for logical control in uncertain and adversarial environments. We provide a proof-of-concept implementation and demonstrate the potential of applying ASCerts in runtime adaptation in a case study.

cs.GT↗

arXiv2026

Sound Probabilistic Safety Bounds for Large Language Models

We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence intervals to obtain probably approximately correct (PAC) bounds for this problem. As our main technical contribution, we propose an algorithm that leverages features in the latent space to prioritize exploring branches in the auto-regressive generation tree that are more likely to produce harmful outputs. Our approach in particular enables the efficient computation of useful lower bounds, even in scenarios where the true harm probability is extremely small, and crucially, the obtained lower bounds are sound, i.e., formally proven to be less than the actual harmfulness probability: our experimental results demonstrate the effectiveness of our method by computing non-trivial lower bounds on state-of-the-art LLMs. This study newly enables the evaluation and statistical certification of LLMs.

cs.CL↗

arXiv2026

Context-Triggered Robust MPC for Temporal Logic Specifications

We consider the problem of synthesizing robust feedback controllers for discrete-time linear systems that ensure the satisfaction of context-dependent linear temporal logic specifications in the presence of additive bounded disturbances. Building on existing results that reduce context-triggered temporal logic synthesis to the realization of context-dependent reach-avoid-stay (cRAS) objectives, we focus on the corresponding low-level control synthesis problem. We first employ certificate-based conditions for the almost-sure satisfaction of RAS specifications. Based on these conditions, we propose a switching control architecture that combines robust model predictive control (MPC) with a local invariant controller, and show that the resulting MPC value function serves as a reachability certificate while avoidance is enforced through robust constraints and the stay is enforced via the local controller. To obtain computationally tractable formulations for the resulting robust optimizations, we employ convex duality to reformulate the robust constraints into equivalent deterministic optimization problems, yielding convex quadratic and second-order cone programs for relevant geometric settings. The proposed framework is demonstrated on a robot navigation problem with context-triggered logical switches in both static and moving environments. The results show significantly larger feasible sets than Lyapunov-based approaches, while naturally accommodating dynamic environments and online task reconfiguration.

eess.SY↗

arXiv2026

Doubly Fair Parity Games

We consider two-player games over finite graphs in which both players are restricted by fairness constraints on their moves. Given a two player game graph $G=(V,E)$ and a set of fair moves $E_f\subseteq E$ a player is said to play "fair" in $G$ if they choose an edge $e \in E_f$ infinitely often whenever the source vertex of $e$ is visited infinitely often. Otherwise, they play "unfair". We equip such games with two $ω$-regular winning conditions $α$ and $β$ deciding the winner of mutually fair and mutually unfair plays, respectively. Whenever one player plays fair and the other plays unfair, the fairly playing player wins the game. The resulting games are called "fair $α/β$ games". We formalize fair $α/β$ games and show that they are determined. For fair parity/parity games, i.e., fair $α/β$ games where $α$ and $β$ are given each by a parity condition over $G$, we provide a polynomial reduction to (normal) parity games via a gadget construction inspired by the reduction of stochastic parity games to parity games. We further give a direct symbolic fixpoint algorithm to solve fair parity/parity games. On a conceptual level, we illustrate the translation between the gadget-based reduction and the direct symbolic algorithm which uncovers the underlying similarities of solution algorithms for fair and stochastic parity games, as well as for the recently considered class of fair games where only one player is restricted by fair moves.

cs.GT↗

arXiv2026

MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents

Tool-using large language model (LLM) agents are increasingly deployed in settings where their reliable behavior is governed by strict procedural manuals. Ensuring that such agents comply with the rules from these manuals is challenging, as they are typically written for humans in natural language while agent behavior manifests as an execution trace of tool calls. Existing evaluations of LLM agents rely on manually constructed benchmarks or LLM-based judges, which either do not scale or lack reliability for complex, long-horizon manuals. To overcome these limitations, we present MANTRA, a framework for automatically synthesizing machine-checkable compliance benchmarks from natural-language manuals and tool schemas. MANTRA independently generates (i) a symbolic world model capturing procedural dependencies, and (ii) a set of trace-level compliance checks for a given task, and validates their consistency using SMT solving. A structured repair loop resolves inconsistencies, requiring human intervention only as a fallback. %This yields benchmarks that are formally validated. Importantly, MANTRA supports arbitrary domains and long procedural manuals, and provides a tunable notion of task complexity which is utilized to automatically derive challenging tasks accompanying compliance checks. Using MANTRA, we build a new benchmark suite with 285 tasks across 6 domains scaling to 50+ page manuals with minimal human effort. Empirically, we show that the compliance checks are richer with stronger constraint enforcement compared to existing benchmarks. Additionally, the granularity of the checks can be used for debugging the agents' failure modes. These results demonstrate that combining automated benchmark generation with formally grounded validation methods enables scalable and reliable benchmarking of tool-using agents.

cs.CL↗

arXiv2026

Incremental Data-Driven Policy Synthesis via Game Abstractions

We address the synthesis of control policies for unknown discrete-time stochastic dynamical systems to satisfy temporal logic objectives. We present a data-driven, abstraction-based control framework that integrates online learning with novel incremental game-solving. Under appropriate continuity assumptions, our method abstracts the system dynamics into a finite stochastic (2.5-player) game graph derived from data. Given a requirement over time on this graph, we compute the winning region -- i.e., the set of initial states from which the objective is satisfiable -- in the resulting game, together with a corresponding control policy. Our main contribution is the construction of abstractions, winning regions and control policies \emph{incrementally}, as data about the system dynamics accumulates. Concretely, our algorithm refines under- and over-approximations of reachable sets for each state-action pair as new data samples arrive. These refinements induce structural modifications in the game graph abstraction -- such as the addition or removal of nodes and edges -- which in turn modify the winning region. Crucially, we show that these updates are inherently monotonic: under-approximations only grow, over-approximations only shrink, and the winning region only expands. We exploit this monotonicity by defining an objective-induced ranking function on the nodes of the abstract game that increases monotonically as new data samples are incorporated. These ranks underpin our novel incremental game-solving algorithm, which employs customized gadgets (DAG-like subgames) within a rank-lifting algorithm to efficiently update the winning region. Numerical case studies demonstrate significant computational savings compared to the baseline approach, which re-solves the entire game from scratch whenever new data samples arrive.

cs.GT↗

arXiv2026

Context-Triggered Contingency Games for Strategic Multi-Agent Interaction

We address the challenge of reliable and efficient interaction in autonomous multi-agent systems, where agents must balance long-term strategic objectives with short-term dynamic adaptation. We propose context-triggered contingency games, a novel integration of strategic games derived from temporal logic specifications with dynamic contingency games solved in real time. Our two-layered architecture leverages strategy templates to guarantee satisfaction of high-level objectives, while a new factor-graph-based solver enables scalable, real-time model predictive control of dynamic interactions. The resulting framework ensures both safety and progress in uncertain, interactive environments. We validate our approach through simulations and hardware experiments in autonomous driving and robotic navigation, demonstrating efficient, reliable, and adaptive multi-agent interaction.

cs.RO↗

arXiv2026

Concurrent Permissive Strategy Templates

Two-player games on finite graphs provide a rigorous foundation for modeling the strategic interaction between reactive systems and their environment. While concurrent game semantics naturally capture the synchronous interactions characteristic of many cyber-physical systems (CPS), their adoption in CPS design remains limited. Building on the concept of permissive strategy templates (PeSTels) for turn-based games, we introduce concurrent (permissive) strategy templates (ConSTels) -- a novel representation for sets of randomized winning strategies in concurrent games with Safety, Büchi, and Co-Büchi objectives. ConSTels compactly encode infinite families of strategies, thereby supporting both offline and online adaptation. Offline, we exploit compositionality to enable incremental synthesis: combining ConSTels for simpler objectives into non-conflicting templates for more complex combined objectives. Online, we demonstrate how ConSTels facilitate runtime adaptation, adjusting action probabilities in response to observed opponent behavior to optimize performance while preserving correctness. We implemented ConSTel synthesis and adaptation in a prototype tool and experimentally show its potential.

cs.GT↗

arXiv2025

Universal Safety Controllers with Learned Prophecies

\emph{Universal Safety Controllers (USCs)} are a promising logical control framework that guarantees the satisfaction of a given temporal safety specification when applied to any realizable plant model. Unlike traditional methods, which synthesize one logical controller over a given detailed plant model, USC synthesis constructs a \emph{generic controller} whose outputs are conditioned by plant behavior, called \emph{prophecies}. Thereby, USCs offer strong generalization and scalability benefits over classical logical controllers. However, the exact computation and verification of prophecies remain computationally challenging. In this paper, we introduce an approximation algorithm for USC synthesis that addresses these limitations via learning. Instead of computing exact prophecies, which reason about sets of trees via automata, we only compute under- and over-approximations from (small) example plants and infer computation tree logic (CTL) formulas as representations of prophecies. The resulting USC generalizes to unseen plants via a verification step and offers improved efficiency and explainability through small and concise CTL prophecies, which remain human-readable and interpretable. Experimental results demonstrate that our learned prophecies remain generalizable, yet are significantly more compact and interpretable than their exact tree automata representations.

cs.LO↗

arXiv2025

Follow the STARs: Dynamic $ω$-Regular Shielding of Learned Policies

This paper presents a novel dynamic post-shielding framework that enforces the full class of $ω$-regular correctness properties over pre-computed probabilistic policies. This constitutes a paradigm shift from the predominant setting of safety-shielding -- i.e., ensuring that nothing bad ever happens -- to a shielding process that additionally enforces liveness -- i.e., ensures that something good eventually happens. At the core, our method uses Strategy-Template-based Adaptive Runtime Shields (STARs), which leverage permissive strategy templates to enable post-shielding with minimal interference. As its main feature, STARs introduce a mechanism to dynamically control interference, allowing a tunable enforcement parameter to balance formal obligations and task-specific behavior at runtime. This allows to trigger more aggressive enforcement when needed, while allowing for optimized policy choices otherwise. In addition, STARs support runtime adaptation to changing specifications or actuator failures, making them especially suited for cyber-physical applications. We evaluate STARs on a mobile robot benchmark to demonstrate their controllable interference when enforcing (incrementally updated) $ω$-regular correctness properties over learned probabilistic policies.

cs.AI↗

arXiv2025

Maximal Adaptation, Minimal Guidance: Permissive Reactive Robot Task Planning with Humans in the Loop

We present a novel framework for human-robot \emph{logical} interaction that enables robots to reliably satisfy (infinite horizon) temporal logic tasks while effectively collaborating with humans who pursue independent and unknown tasks. The framework combines two key capabilities: (i) \emph{maximal adaptation} enables the robot to adjust its strategy \emph{online} to exploit human behavior for cooperation whenever possible, and (ii) \emph{minimal tunable feedback} enables the robot to request cooperation by the human online only when necessary to guarantee progress. This balance minimizes human-robot interference, preserves human autonomy, and ensures persistent robot task satisfaction even under conflicting human goals. We validate the approach in a real-world block-manipulation task with a Franka Emika Panda robotic arm and in the Overcooked-AI benchmark, demonstrating that our method produces rich, \emph{emergent} cooperative behaviors beyond the reach of existing approaches, while maintaining strong formal guarantees.

cs.RO↗

arXiv2025

Data-Driven Abstraction and Synthesis for Stochastic Systems with Unknown Dynamics

We study the automated abstraction-based synthesis of correct-by-construction control policies for stochastic dynamical systems with unknown dynamics. Our approach is to learn an abstraction from sampled data, which is represented in the form of a finite Markov decision process (MDP). In this paper, we present a data-driven technique for constructing finite-state interval MDP (IMDP) abstractions of stochastic systems with unknown nonlinear dynamics. As a distinguishing and novel feature, our technique only requires (1) noisy state-input-state observations and (2) an upper bound on the system's Lipschitz constant. Combined with standard model-checking techniques, our IMDP abstractions enable the synthesis of policies that satisfy probabilistic temporal properties (such as "reach-while-avoid") with a predefined confidence. Our experimental results show the effectiveness and robustness of our approach.

eess.SY↗

arXiv2025

Quantitative Strategy Templates

This paper presents (permissive) \emph{Quantitative Strategy Templates} (QaSTels) to succinctly represent infinitely many winning strategies in two-player energy and mean-payoff games. This transfers the recently introduced concept of \emph{Permissive (qualitative) Strategy Templates} (PeSTels) for $ω$-regular games to games with quantitative objectives. We provide the theoretical and algorithmic foundations of (i) QaSTel synthesis, and (ii) their (incremental) combination with PeSTels for games with mixed quantitative and qualitative objectives. Using a prototype implementation of our synthesis algorithms, we demonstrate empirically that QaSTels extend the advantageous properties of strategy templates over single winning strategies -- known from PeSTels -- to games with (additional) quantitative objectives. This includes (i) the enhanced robustness of strategies due to their runtime-adaptability, and (ii) the compositionality of templates w.r.t. incrementally arriving objectives. We use control-inspired examples to illustrate these superior properties of QaSTels for CPS design.

cs.GT↗

arXiv2025

Synthesis of Universal Safety Controllers

The goal of logical controller synthesis is to automatically compute a control strategy that regulates the discrete, event-driven behavior of a given plant s.t. a temporal logic specification holds over all remaining traces. Standard approaches to this problem construct a two-player game by composing a given complete plant model and the logical specification and applying standard algorithmic techniques to extract a control strategy. However, due to the often enormous state space of a complete plant model, this process can become computationally infeasible. In this paper, we introduce a novel synthesis approach that constructs a universal controller derived solely from the game obtained by the standard translation of the logical specification. The universal controller's moves are annotated with prophecies - predictions about the plant's behavior that ensure the move is safe. By evaluating these prophecies, the universal controller can be adapted to any plant over which the synthesis problem is realizable. This approach offers several key benefits, including enhanced scalability with respect to the plant's size, adaptability to changes in the plant, and improved explainability of the resulting control strategy. We also present encouraging experimental results obtained with our prototype tool, UNICON.

cs.LO↗

arXiv2025

Fair Quantitative Games

We examine two-player games over finite weighted graphs with quantitative (mean-payoff or energy) objective, where one of the players additionally needs to satisfy a fairness objective. The specific fairness we consider is called 'strong transition fairness', given by a subset of edges of one of the players, which asks the player to take fair edges infinitely often if their source nodes are visited infinitely often. We show that when fairness is imposed on player 1, these games fall within the class of previously studied omega-regular mean-payoff and energy games. On the other hand, when the fairness is on player 2, to the best of our knowledge, these games have not been previously studied. We provide gadget-based algorithms for fair mean-payoff games where fairness is imposed on either player, and for fair energy games where the fairness is imposed on player 1. For all variants of fair mean-payoff and fair energy (under unknown initial credit) games, we give pseudo-polynomial algorithms to compute the winning regions of both players. Additionally, we analyze the strategy complexities required for these games. Our work is the first to extend the study of strong transition fairness, as well as gadget-based approaches, to the quantitative setting. We thereby demonstrate that the simplicity of strong transition fairness, as well as the applicability of gadget-based techniques, can be leveraged beyond the omega-regular domain.

cs.GT↗

arXiv2024

Localized Attractor Computations for Infinite-State Games (Full Version)

Infinite-state games are a commonly used model for the synthesis of reactive systems with unbounded data domains. Symbolic methods for solving such games need to be able to construct intricate arguments to establish the existence of winning strategies. Often, large problem instances require prohibitively complex arguments. Therefore, techniques that identify smaller and simpler sub-problems and exploit the respective results for the given game-solving task are highly desirable. In this paper, we propose the first such technique for infinite-state games. The main idea is to enhance symbolic game-solving with the results of localized attractor computations performed in sub-games. The crux of our approach lies in identifying useful sub-games by computing permissive winning strategy templates in finite abstractions of the infinite-state game. The experimental evaluation of our method demonstrates that it outperforms existing techniques and is applicable to infinite-state games beyond the state of the art.

cs.LO↗

arXiv2024

Contract-Based Distributed Synthesis in Two-Objective Parity Games

We present a novel method to compute $\textit{assume-guarantee contracts}$ in non-zerosum two-player games over finite graphs where each player has a different $ ω$-regular winning condition. Given a game graph $G$ and two parity winning conditions $Φ_0$ and $Φ_1$ over $G$, we compute $\textit{contracted strategy-masks}$ ($\texttt{csm}$) $(Ψ_{i},Φ_{i})$ for each Player $i$. Within a $\texttt{csm}$, $Φ_{i}$ is a $\textit{permissive strategy template}$ which collects an infinite number of winning strategies for Player $i$ under the assumption that Player $1-i$ chooses any strategy from the $\textit{permissive assumption template}$ $Ψ_{i}$. The main feature of $\texttt{csm}$'s is their power to $\textit{fully decentralize all remaining strategy choices}$ -- if the two player's $\texttt{csm}$'s are compatible, they provide a pair of new local specifications $Φ_0^\bullet$ and $Φ_1^\bullet$ such that Player $i$ can locally and fully independently choose any strategy satisfying $Φ_i^\bullet$ and the resulting strategy profile is ensured to be winning in the original two-objective game $(G,Φ_0,Φ_1)$. In addition, the new specifications $Φ_i^\bullet$ are $\textit{maximally cooperative}$, i.e., allow for the distributed synthesis of any cooperative solution. Further, our algorithmic computation of $\texttt{csm}$'s is complete and ensured to terminate. We illustrate how the unique features of our synthesis framework effectively address multiple challenges in the context of \enquote{correct-by-design} logical control software synthesis for cyber-physical systems and provide empirical evidence that our approach possess desirable structural and computational properties compared to state-of-the-art techniques.

cs.GT↗

arXiv2024

Most General Winning Secure Equilibria Synthesis in Graph Games

This paper considers the problem of co-synthesis in $k$-player games over a finite graph where each player has an individual $ω$-regular specification $ϕ_i$. In this context, a secure equilibrium (SE) is a Nash equilibrium w.r.t. the lexicographically ordered objectives of each player to first satisfy their own specification, and second, to falsify other players' specifications. A winning secure equilibrium (WSE) is an SE strategy profile $(π_i)_{i\in[1;k]}$ that ensures the specification $ϕ:=\bigwedge_{i\in[1;k]}ϕ_i$ if no player deviates from their strategy $π_i$. Distributed implementations generated from a WSE make components act rationally by ensuring that a deviation from the WSE strategy profile is immediately punished by a retaliating strategy that makes the involved players lose. In this paper, we move from deviation punishment in WSE-based implementations to a distributed, assume-guarantee based realization of WSE. This shift is obtained by generalizing WSE from strategy profiles to specification profiles $(φ_i)_{i\in[1;k]}$ with $\bigwedge_{i\in[1;k]}φ_i = ϕ$, which we call most general winning secure equilibria (GWSE). Such GWSE have the property that each player can individually pick a strategy $π_i$ winning for $φ_i$ (against all other players) and all resulting strategy profiles $(π_i)_{i\in[1;k]}$ are guaranteed to be a WSE. The obtained flexibility in players' strategy choices can be utilized for robustness and adaptability of local implementations. Concretely, our contribution is three-fold: (1) we formalize GWSE for $k$-player games over finite graphs, where each player has an $ω$-regular specification $ϕ_i$; (2) we devise an iterative semi-algorithm for GWSE synthesis in such games, and (3) obtain an exponential-time algorithm for GWSE synthesis with parity specifications $ϕ_i$.

cs.GT↗