arXiv subjects

Rémi Delmas

Publications and source records attributed to Rémi Delmas.

5 recordsLinked to original sources

arXiv2026

A Neurosymbolic Approach to Natural Language Formalization and Verification

Large Language Models perform well at natural language interpretation and reasoning, but their lack of formal correctness guarantees limits their adoption in regulated industries like finance and health-care that operate under strict policies. To address this limitation, we launched Automated Reasoning checks (ARc): a public service that (1) uses LLMs with optional human guidance to formalize natural language policies, allowing fine-grained control of the formalization process, and (2) uses inference-time autoformalization to validate logical correctness of natural language statements against those policies. ARc performs multiple redundant formalization steps at inference time, checking the formalizations for semantic equivalence. Our benchmarks show that ARc exceeds 99% soundness and achieves a near-zero false positive rate in identifying logical validity. Our approach produces auditable artifacts that substantiate the verification outcomes and can be used to improve the original text. ARc is the first commercial offering from a major cloud provider to integrate automated reasoning into a generative AI guardrail.

cs.CL↗

arXiv2026

Kani: A Model Checker for Rust

Rust's ownership type system prevents memory errors in safe code, but certain desirable properties remain orthogonal to compilation: the soundness of unsafe operations (e.g., raw pointer dereferences), functional correctness, and absence of runtime panics. We present Kani, an open-source model checker for Rust that pushes bounded model checking beyond bug-finding to provide correctness guarantees for these properties. Kani compiles proof harnesses from Rust's Mid-level Intermediate Representation (MIR) into CBMC's bit-precise verification engine, automatically checking a comprehensive set of safety properties with no user annotation. To extend verification from bounded to unbounded, Kani provides a specification language comprising function contracts, loop contracts, quantifiers, and function stubbing. We demonstrate feasibility through case studies on industrial Rust projects, where contracts upgraded verification from panic-freedom to functional correctness, uncovering six previously unknown bugs. Kani operates at scale in production CI, with over 16,000 harnesses verified per code change in the Rust standard library verification campaign.

cs.SE↗

arXiv2022

Passenger-Centric Urban Air Mobility: Fairness Trade-Offs and Operational Efficiency

Urban Air Mobility (UAM) has the potential to revolutionize transportation. It will exploit the third dimension to help smooth ground traffic in densely populated areas. To be successful, it will require an integrated approach able to balance efficiency and safety while harnessing common resources and information. In this work we focus on future urban air-taxi services, and present the first methods and algorithms to efficiently operate air-taxi at scale. Our approach is twofold. First, we use a passenger-centric perspective which introduces traveling classes, and information sharing between transport modes to differentiate quality of services. This helps smooth multimodal journeys and increase passenger satisfaction. Second, we provide a flight routing and recharging solution which minimizes direct operational costs while preserving long term battery life through reduced energy-intense recharging. Our methods, which surpass the performance of a general state-of-the-art commercial solver, are also used to gain meaningful insights on the design space of the air-taxi problem, including solutions to hidden fairness issues.

math.OC↗

arXiv2021

Reinforcement Learning with Formal Performance Metrics for Quadcopter Attitude Control under Non-nominal Contexts

We explore the reinforcement learning approach to designing controllers by extensively discussing the case of a quadcopter attitude controller. We provide all details allowing to reproduce our approach, starting with a model of the dynamics of a crazyflie 2.0 under various nominal and non-nominal conditions, including partial motor failures and wind gusts. We develop a robust form of a signal temporal logic to quantitatively evaluate the vehicle's behavior and measure the performance of controllers. The paper thoroughly describes the choices in training algorithms, neural net architecture, hyperparameters, observation space in view of the different performance metrics we have introduced. We discuss the robustness of the obtained controllers, both to partial loss of power for one rotor and to wind gusts and finish by drawing conclusions on practical controller design by reinforcement learning.

cs.AI↗

arXiv2013

Generating Property-Directed Potential Invariants By Backward Analysis

This paper addresses the issue of lemma generation in a k-induction-based formal analysis of transition systems, in the linear real/integer arithmetic fragment. A backward analysis, powered by quantifier elimination, is used to output preimages of the negation of the proof objective, viewed as unauthorized states, or gray states. Two heuristics are proposed to take advantage of this source of information. First, a thorough exploration of the possible partitionings of the gray state space discovers new relations between state variables, representing potential invariants. Second, an inexact exploration regroups and over-approximates disjoint areas of the gray state space, also to discover new relations between state variables. k-induction is used to isolate the invariants and check if they strengthen the proof objective. These heuristics can be used on the first preimage of the backward exploration, and each time a new one is output, refining the information on the gray states. In our context of critical avionics embedded systems, we show that our approach is able to outperform other academic or commercial tools on examples of interest in our application field. The method is introduced and motivated through two main examples, one of which was provided by Rockwell Collins, in a collaborative formal verification framework.

cs.LO↗