Foundations of Semantic Reasoning for Enhanced AI Cooperation in 6G Multi-Agent Communications
This PhD research project focuses on pioneering foundational theories in semantic communications, specifically by advancing the compositional learning and reasoning capabilities of AI agents within multi-agent environments. The goal is to enable AI-driven systems to selectively extract, interpret, and exchange semantically meaningful information in a goal-oriented and context-sensitive manner, moving beyond traditional data-oriented communications. Integrated Sensing and Communication (ISAC) will serve as a validation ground, introducing unique constraints related to resource optimization, multi-modal sensing, and environmental adaptability. However, the primary aim is to establish broadly applicable methodologies that enhance semantic information exchange and cooperation among AI agents. This involves rethinking the combination of modeling, numerical simulation, and experimental validation to effectively implement AI-driven semantic information exchange.
Magnetic DIsks as Transducer of Angular Momentum
The proposed topic is a collaborative project to exploit suspended magnetic disks as novel microwave transducers of orbital angular momentum. Our goal is to develop ultra-high fidelity opto-mechanical modulators operating at GHz frequencies by integrating magnetic materials into optical components. This innovative concept arises from recent progress in the study of angular momentum conservation laws by magnon modes in axi-symmetric cavities, leading to new opportunities to develop a more frugal, agile, and sustainable communications technology. Our proposed design has the potential to achieve coherent interconversion between the microwave frequency range in which wireless networks or quantum computers operate and optical network frequencies, which is the optimal frequency range for long-distance communications. In this regard, our proposal not only proposes new applications of magnonics to the field of optics not previously envisioned, but also builds a bridge between the spintronics and the electronic and quantum communities.
In this proposal, the elastic deformations are generated by the magnetization dynamics through the magneto-elastic tensor and its contactless coupling to a microwave circuit. We have shown that coherent coupling between magnons and phonons can be achieved by precisely tuning the magnetic resonance degenerate with a selected elastic mode via the application of an external magnetic field. We expect to achieve ultra-high fidelity conversion by focusing our study on micron-sized single crystal magnetic garnet structures integrated with GaAs photonic waveguides or cavities. In addition, we propose the fabrication of suspended cavities as a means to minimize further energy leakage (elastic or optical) through the substrate.
The first challenge is to produce hybrid materials that integrate high quality garnet films with semiconductors. We propose a radically new approach based on micron-thick magnetic garnet films grown by liquid phase epitaxy (LPE) on a gadolinium-gallium-garnet (GGG) substrate. The originality is to bond the flipped film to a semiconductor wafer and then remove most of the the GGG substrate by mechanical polishing. The resulting multi-layer is then processed using standard lithography techniques, taking advantage of the relative robustness of garnet materials to chemical, thermal or milling processes.
The second challenge is to go beyond the excitation of uniform modes and target modes with orbital angular momentum as encoders of arbitrarily large quanta of nJ? for mode multiplexed communication channels or multi-level quantum state registers. The project will take advantage of recent advances in spin-orbit coupling between azimuthal spin waves as well as elastic scattering of magnons on anisotropic magneto-crystalline tensors. In this project, we also want to go beyond uniformly magnetized state and exploit the ability to continuously morph the equilibrium magnetic texture in the azimuthal direction as a means of engineering the selection rules and thus coherently access otherwise hidden mode symmetries.
Advancing Semantic Representation, Alignment, and Reasoning in Multi-Agent 6G Communication Systems
Semantic communications is an emerging and transformative research area, where the focus shifts from transmitting raw data to conveying meaningful information. While initial models and design solutions have laid foundational principles, they often rest on strong assumptions regarding the extraction, representation, and interpretation of semantic content. The advent of 6G networks introduces new challenges, particularly with the growing need for multi-agent systems where multiple AI-driven agents interact seamlessly.
In this context, the challenge of semantic alignment becomes critical. Existing literature on multi-agent semantic communications frequently assumes that all agents share a common understanding and interpretation framework, a condition rarely met in practical scenarios. Misaligned representations can lead to communication inefficiencies, loss of critical information, and misinterpretations.
This PhD research aims to advance the state-of-the-art by investigating the principles of semantic representation, alignment, and reasoning in multi-AI agent environments within 6G communication networks. The study will explore how agents can dynamically align their semantic models, ensuring consistent interpretation of messages while accounting for differences in context, objectives, and prior knowledge. By leveraging techniques from artificial intelligence, such as machine learning, ontology alignment, and multi-agent reasoning, the goal is to propose novel frameworks that enhance communication efficiency and effectiveness in multi-agent settings. This work will contribute to more adaptive, intelligent, and context-aware communication systems that are key to the evolution of 6G networks.
Enhancing Communication Security Through Faster-than-Nyquist Transceiver Design
In light of the growing demand for transmission capacity in communication networks, it is essential to explore innovative techniques that enhance spectral efficiency while maintaining the reliability and security of transmission links. This project proposes a comprehensive theoretical modeling of Faster-Than-Nyquist (FTN) systems, accompanied by simulations and numerical analyses to evaluate their performance in various communication scenarios. The study will aim to identify the necessary trade-offs to maximize transmission rates while considering the constraints related to implementation complexity and transmission security, a crucial issue in an increasingly vulnerable environment to cyber threats. This work will help identify opportunities for capacity enhancement while highlighting the technological challenges and adjustments necessary for the widespread adoption of these systems for critical and secure links.
Super-gain miniature antennas with circular polarization and electronic beam steering
Antenna radiation control in terms of shape and polarization is a key element for future communication systems. Directive compact antennas offer new opportunities for wireless applications in terms of spatial selectivity and filtering. This leads to a reduction in electromagnetic pollution by mitigating interferences with other communication systems and reducing battery consumption in compact smart devices (IoT), while enabling also new use modes. However, the conventional techniques for enhancing the directivity often lead to a significant increase of the antenna size. Consequently, the integration of directional antennas in small wireless devices is limited. This difficulty is particularly critical for the frequency bands below 3 GHz if object dimensions are limited to a few centimeters. Super directive/gain compact antennas with beam-steering capabilities and operating on a wideband or on multi-bands are an innovative and attractive solution for the development of new applications in the field of the connected objects. In fact, the possibility to control electronically the antenna radiation properties is an important characteristic for the development of the future generation and smart communication systems. CEA Leti has a very strong expertise in the domain of superdirective antennas demonstrating the potentials of the use of ultra-compact parasitic antenna arrays. This PhD project will take place at CEA Leti Grenoble in the antennas and propagation laboratory (LAPCI). The main objectives of this work are: i) contribution to development of numerical tools for the design and optimization of superdirective compact arrays with beam-steering capabilities; ii) the study of new elementary sources for compact antenna arrays; iii) the realization and experimental characterization of a supergain compact array with circular polarization and beam-steering capabilities. This work will combine theoretical studies and model developments, antenna design using 3D electromagnetic software, prototyping and experimentations.