arXiv subjects

I. de Zarzà

Publications and source records attributed to I. de Zarzà.

13 recordsLinked to original sources

arXiv2026

Strategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical Systems

LLM-agent evaluations commonly measure task success or agreement with a declared plan. In strategic cyber-physical systems, an architecture must also remain appropriate after autonomous participants respond and physics constrains outcomes. We introduce a controlled benchmark of planning-induced control trajectories: ordered planning operations and directives linking execution architecture to strategic response and physical consequences. Four coded executors (predefined, sequential, hierarchical, and search) control demand response for 40 prosumers on a radial feeder. The LLM declares or advises typed policies and mediates communication; schedules, base prosumer dynamics, stochastic actions, and power flow remain explicit code. Paired forced-mode counterfactuals, exact-prompt caching, common response draws with separate randomness streams, critic isolation, and event-level feasibility isolate comparisons. The Llama-3.3-70B experiments on this feeder distinguish three properties. First, forced search is the oracle in all five baseline seeds under the specified objective. Second, injected objective substitution preserves mode agreement at 1.0 while increasing cumulative voltage shortfall by 2.68x. Third, the 144-scenario, 576-episode factorial bank, using three repeated seeds, contains feasible oracles from predefined, sequential, and search. The prespecified stress-held-out ridge has mean regret 90.7 and no observed value over fixed sequential. A post-hoc constraint-aware analysis reduces regret to 29.0; a simple deadline rule attains 28.7, so this gain does not establish a learning advantage. An all-feasible ablation does not improve over fixed search. These are simulation-internal, descriptive comparisons. A five-model, 300-declaration extension tests interface behaviour, not cross-backbone physical rankings; shared-endpoint latency tails motivate probabilistic live feasibility.

cs.MA↗

arXiv2026

Verifier-guided discovery of exact high-order mimetic operators with large language models

Designing a high-order structure-preserving discretization is a constrained mathematical search: conservation, a positive discrete inner product, physical spectral behavior, boundary accuracy, bandwidth, and partial differential equation (PDE) error must hold simultaneously. We test whether large language models (LLMs) can help while remaining non-authoritative. The motivating MOLE implementation of the Corbino-Castillo staggered operators satisfies a general discrete Gauss identity and conserves exactly, yet its order-six and order-eight Dirichlet blocks develop four non-real boundary-localized modes. An endpoint-supported positive-definite identity would instead force a real non-positive spectrum, so the search changes the closure and norm architecture. An LLM proposes only a typed construction program; a deterministic linear-program compiler generates coefficients; an independent verifier tests algebra, positivity, physical modes, conditioning, and manufactured PDEs; and coupled rational reconstruction provides exact certificates. Across 1,200 solver evaluations, an externally fixed verifier accepted 55.0% of full-metric-feedback proposals and 53.3% of illumination-archive proposals, versus 13.3% for uniform random search. Four leading LLM-originated programs were reconstructed exactly. The strongest order-six-interior, order-four-boundary candidate lowers the prior positive-diagonal spectral-radius constant by 25.4% and its PDE error 62.7-fold. Its certified heat-equation energy is contractive, whereas the order-six reference exhibits 6.6% transient growth; both have the same RK4 stability limit. The LLM proposes structural hypotheses; deterministic mathematics determines validity.

math.NA↗

arXiv2026

Visual Grounding in Zero-Shot Vision-Language Control

Vision-language models (VLMs) are increasingly used as zero-shot controllers, but successful trajectories do not necessarily show that decisions are grounded in visual input: simulator dynamics and conservative action priors can produce favourable scores without meaningful perception. We investigate this with an input-ablation battery: blind-image controls, repeated identical inputs, lane-axis reflection, non-visual baselines, and pipeline-integrity checks. Across nine direct-action models, six structured local VLMs, and an exploratory VLM-MPC hierarchy, we analyse 32,874 scored calls over two embodiments and three simulators. The direct-control results are largely negative: a constant-SLOW policy outperforms a scripted geometric controller, several models are image-invariant or nearly constant, and models that recognize longitudinal hazards still fail to transform LEFT and RIGHT under reflection. No local VLM meets the joint longitudinal and lateral grounding criteria. However, an image-only deterministic positive control estimates the lead gap with 0.090 m MAE and exact mirror equivariance, confirming the stimuli carry sufficient visual information; the failures are modular, not universal. A post-hoc, leakage-controlled symmetry-consensus guardian selects two models from 16 calibration frames and freezes a 2-of-4 hazard vote across original and reflected views. On 272 held-out frames it reaches 0.954 balanced accuracy (episode-cluster bootstrap 95% CI [0.895,0.990]); nested leave-one-episode-out recovers the same pair and threshold in all 12 folds. Abstaining on ties raises committed balanced accuracy to 0.973 at 0.824 coverage. With deterministic perception retaining lateral authority, offline modular replay achieves 0.934 action agreement and exact mirror equivariance. These results support current VLMs as bounded, selective hazard assistants, not monolithic zero-shot controllers.

cs.RO↗

arXiv2026

Foundation Models for Automatic CAD Generation

Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) enable the automatic generation of parametric 3D designs from natural-language specifications. This chapter presents an empirical study of foundation models for automatic Computer-Aided Design (CAD) generation of mechanical parts, using a unified evaluation pipeline and a curated benchmark of 97 engineering design problems. We introduce LLMForge, a multi-model text-to-CAD framework integrating JSON-schema validation, analytic feature scoring, mesh synthesis, and multi-round iterative refinement, studied under two critique regimes. IterTracer uses a Phong-shaded ray-trace renderer with analytic visual metrics (silhouette IoU, hole visibility, edge clearance, aspect-ratio conformance) for lightweight geometry-aware feedback across rounds. IterVision replaces the analytic scorer with a VLM semantic critic (Qwen2.5-VL-72B) that evaluates rendered views via chain-of-thought visual reasoning, assessing spatial coherence and design intent. On a benchmark spanning four canonical geometry families (plates with holes and bolt circles, multi-feature boxes, flanged cylinders, and L-brackets), we evaluate seven foundation models: DeepSeek-V3.2, Qwen3-235B-A22B, Llama-3.3-70B, Gemma-3-27B, GLM-4.5, MiniMax-M2.1, and INTELLECT. Under IterTracer, the four highest-ranked models form a tight cluster (overall mean in [0.885, 0.890]) with 98.97% mesh success, showing that compact instruction-tuned models can match substantially larger systems. VLM-based critique in IterVision yields 100% watertight mesh generation on the leading model while surfacing systematic difficulty on rotationally symmetric geometries such as cylinders, where visual and semantic scoring diverge most. We discuss benchmark design, failure modes, CAD-oriented prompting, and implications for industrial workflows and scalable automated mechanical design.

cs.AI↗

arXiv2026

Collective Intelligence with Foundation Models

As foundation models grow in scale and diversity, coordinating multiple models into cooperative reasoning systems offers a path toward safer, more reliable AI. This chapter presents a multi-agent framework where solver models generate independent drafts, each undergoes structured critique and revision by a critic agent, and an aggregator agent synthesizes a final consensus solution. A scoring module provides semantic, numerical, and procedural evaluation across all agents. Through ablation studies on a benchmark spanning calculus, physics, chemistry, biology, economics, optimization, statistics, and mathematics, we isolate the contributions of framework architecture versus model diversity. We compare four configurations: (1) Individual Baseline, (2) Homogeneous Framework using one shared model, (3) Redundant Homogeneous Solvers using multiple instances of the same model, and (4) Heterogeneous Framework with diverse specialized models. Results show that while framework structure and redundant sampling yield modest gains, model heterogeneity is the critical factor driving substantial performance improvements. The heterogeneous configuration achieves superior step-wise accuracy (0.64 vs. 0.54 for individual models; 2.3x improvement over homogeneous configurations) with reduced variance across categories and difficulty levels. Step-wise reasoning quality (correctness of intermediate steps, not just final answers) improves dramatically only with model diversity, showing that heterogeneous agents provide complementary error detection and reasoning refinement essential for explainability and auditability. We discuss architectural principles, evaluation methodology, and implications for Global Applied AI, showing how heterogeneous multi-agent coordination supports transparent, auditable, high-confidence decision-making across scientific and industrial domains.

cs.MA↗

arXiv2026

LLM-Mediated Demand Response Coordination in Smart Microgrids

Effective demand response in smart microgrids requires prosumers to cooperate voluntarily under strategic self-interest, a coordination problem structurally equivalent to a repeated Prisoner's Dilemma on a social network. This paper presents a multi-agent simulation in which a Large Language Model (LLM) Influence Compiler issues structured demand-response directives to a population of heterogeneous prosumer agents, each governed by a hybrid decision architecture combining game-theoretic base probability (derived from payoff history, neighbour imitation, and exploitation memory) with LLM narrative evaluation of incoming coordination signals. The hybrid architecture resolves a key methodological challenge: LLMs aligned via Reinforcement Learning from Human Feedback (RLHF) exhibit strong cooperation bias when used as direct decision-makers, producing flat dynamics regardless of grid conditions. By separating strategic reasoning from grounded narrative evaluation, the model generates realistic prosumer behaviour across six personality archetypes, with baseline cooperation near 50% and clear differentiation under influence. Compiled structured directives achieve 33.3% demand-curtailment cooperation versus 27.0% for unstructured messaging and 28.0% for a no-intervention baseline ($Δ_\mathrm{comp} = +0.063$), with the advantage preserved across both grounded and idealized agent substrates ($Δ= +0.083$) and across all resistance levels ($R = 0.1$ to $0.7$). Hub-targeted dissemination via high-centrality network nodes outperforms peripheral or random targeting, confirming that grid topology provides mechanistic amplification independent of message content. These results suggest that structured LLM compilation, grounded agent reasoning, and network-aware targeting are complementary design principles for scalable, interpretable demand-response coordination in smart-city energy systems.

cs.MA↗

arXiv2026

Language-Conditioned Visual Grounding with CLIP Multilingual

Multilingual vision-language models exhibit systematic performance gaps across languages, but the mechanism remains ambiguous: cross-language divergence could arise from the visual encoder, the text branch, or their interaction. We resolve this ambiguity through a dense multilingual CLIP probe in which the visual encoder is held identical across thirteen typologically diverse languages and only the XLM-RoBERTa text branch varies. We evaluate two CLIP architectures spanning a 7x visual-encoder scale gap (XLM-R base + ViT-B/32, ~87M visual parameters; XLM-R large + ViT-H/14, ~632M) on 11 concepts and 210 images, and quantify cross-language agreement via cluster-mask IoU, top-percentile IoU, and Spearman rank correlation against an English reference (n=2,310 paired observations per language). Three findings emerge. First, low-resource languages (Arabic, Basque, Luxembourgish) incur a structural penalty at both backbone scales (Wilcoxon HR>LR p<10^-300; cluster-mask IoU gap +0.114 at base, +0.143 at large), isolating the deficit to the text branch. Second, scaling the encoder 7x widens the gap for structural failure cases (Basque Δ=-0.056, Luxembourgish Δ=-0.076) while improving Arabic (Δ=+0.033), separating corpus-coverage from tokeniser-fertility failures. Third, peak similarity is preserved across languages (mean ratio 0.94 at large scale) while cluster-mask IoU drops sharply, identifying spatial misalignment, not signal collapse, as the dominant failure mode. At 3.4-3.9 Wh per 1,000 queries, dense-CLIP grounding is competitive with high-throughput inference budgets, positioning it as a practical substrate for energy-aware multilingual deployment.

cs.CL↗

arXiv2026

A Computational Framework for Cross-Domain Mission Design and Onboard Cognitive Decision Support

The design of distributed autonomous systems for operation beyond reliable ground contact presents a fundamental tension: as round-trip communication latency grows, the set of decisions delegable to ground operators shrinks. This paper establishes a unified computational methodology for quantifying and comparing this constraint across seven heterogeneous mission architectures, spanning Earth low-orbit surveillance constellations, Mars orbital navigation systems, autonomous underwater mine-clearing swarms, deep-space inter-satellite link networks, and outer-planet in-situ buoy platforms. We introduce the Autonomy Necessity Score, a log-domain latency metric mapping each system continuously from the ground-dependent to the fully-autonomous regime, grounded in nine independently validated computational studies covering Walker spherical-cap coverage mechanics, infrared Neyman-Pearson detection, Extended Kalman Filter hypersonic tracking, cross-mission RF and acoustic link budgets spanning seven orders of magnitude in range, Monte Carlo science-yield sensitivity for TDMA inter-satellite protocols, cross-architecture power budget sizing, distributed magnetic-signature formation emulation, and Arrhenius-corrected cryogenic swarm reliability. Building on this foundation, we evaluate an LLM-based Autonomous Mission Decision Support layer in which three foundation models (Llama-3.3-70B, DeepSeek-V3, and Qwen3-A22B) are queried live via the Nebius AI Studio API across ten structured anomaly scenarios derived directly from the preceding analyses. The best-performing model achieves 80% decision accuracy against physics-grounded ground truth, with all 180 inference calls completing within a 2 s latency budget consistent with radiation-hardened edge deployment, establishing the viability of foundation models as an onboard cognitive layer for high-ANS missions.

eess.SY↗

arXiv2026

Semantic Invariance in Agentic AI

Large Language Models (LLMs) increasingly serve as autonomous reasoning agents in decision support, scientific problem-solving, and multi-agent coordination systems. However, deploying LLM agents in consequential applications requires assurance that their reasoning remains stable under semantically equivalent input variations, a property we term semantic invariance. Standard benchmark evaluations, which assess accuracy on fixed, canonical problem formulations, fail to capture this critical reliability dimension. To address this shortcoming, in this paper we present a metamorphic testing framework for systematically assessing the robustness of LLM reasoning agents, applying eight semantic-preserving transformations (identity, paraphrase, fact reordering, expansion, contraction, academic context, business context, and contrastive formulation) across seven foundation models spanning four distinct architectural families: Hermes (70B, 405B), Qwen3 (30B-A3B, 235B-A22B), DeepSeek-R1, and gpt-oss (20B, 120B). Our evaluation encompasses 19 multi-step reasoning problems across eight scientific domains. The results reveal that model scale does not predict robustness: the smaller Qwen3-30B-A3B achieves the highest stability (79.6% invariant responses, semantic similarity 0.91), while larger models exhibit greater fragility.

cs.AI↗

arXiv2026

LLM Constitutional Multi-Agent Governance

Large Language Models (LLMs) can generate persuasive influence strategies that shift cooperative behavior in multi-agent populations, but a critical question remains: does the resulting cooperation reflect genuine prosocial alignment, or does it mask erosion of agent autonomy, epistemic integrity, and distributional fairness? We introduce Constitutional Multi-Agent Governance (CMAG), a two-stage framework that interposes between an LLM policy compiler and a networked agent population, combining hard constraint filtering with soft penalized-utility optimization that balances cooperation potential against manipulation risk and autonomy pressure. We propose the Ethical Cooperation Score (ECS), a multiplicative composite of cooperation, autonomy, integrity, and fairness that penalizes cooperation achieved through manipulative means. In experiments on scale-free networks of 80 agents under adversarial conditions (70% violating candidates), we benchmark three regimes: full CMAG, naive filtering, and unconstrained optimization. While unconstrained optimization achieves the highest raw cooperation (0.873), it yields the lowest ECS (0.645) due to severe autonomy erosion (0.867) and fairness degradation (0.888). CMAG attains an ECS of 0.741, a 14.9% improvement, while preserving autonomy at 0.985 and integrity at 0.995, with only modest cooperation reduction to 0.770. The naive ablation (ECS = 0.733) confirms that hard constraints alone are insufficient. Pareto analysis shows CMAG dominates the cooperation-autonomy trade-off space, and governance reduces hub-periphery exposure disparities by over 60%. These findings establish that cooperation is not inherently desirable without governance: constitutional constraints are necessary to ensure that LLM-mediated influence produces ethically stable outcomes rather than manipulative equilibria.

cs.MA↗

arXiv2025

Cross-Platform Evaluation of Reasoning Capabilities in Foundation Models

This paper presents a comprehensive cross-platform evaluation of reasoning capabilities in contemporary foundation models, establishing an infrastructure-agnostic benchmark across three computational paradigms: HPC supercomputing (MareNostrum 5), cloud platforms (Nebius AI Studio), and university clusters (a node with eight H200 GPUs). We evaluate 15 foundation models across 79 problems spanning eight academic domains (Physics, Mathematics, Chemistry, Economics, Biology, Statistics, Calculus, and Optimization) through three experimental phases: (1) Baseline establishment: Six models (Mixtral-8x7B, Phi-3, LLaMA 3.1-8B, Gemma-2-9b, Mistral-7B, OLMo-7B) evaluated on 19 problems using MareNostrum 5, establishing methodology and reference performance; (2) Infrastructure validation: The 19-problem benchmark repeated on university cluster (seven models including Falcon-Mamba state-space architecture) and Nebius AI Studio (nine state-of-the-art models: Hermes-4 70B/405B, LLaMA 3.1-405B/3.3-70B, Qwen3 30B/235B, DeepSeek-R1, GPT-OSS 20B/120B) to confirm infrastructure-agnostic reproducibility; (3) Extended evaluation: Full 79-problem assessment on both university cluster and Nebius platforms, probing generalization at scale across architectural diversity. The findings challenge conventional scaling assumptions, establish training data quality as more critical than model size, and provide actionable guidelines for model selection across educational, production, and research contexts. The tri-infrastructure methodology and 79-problem benchmark enable longitudinal tracking of reasoning capabilities as foundation models evolve.

cs.AI↗

arXiv2025

Advanced System Engineering Approaches to Emerging Challenges in Planetary and Deep-Space Exploration

This paper presents innovative solutions to critical challenges in planetary and deep-space exploration electronics. We synthesize findings across diverse mission profiles, highlighting advances in: (1) MARTIAN positioning systems with dual-frequency transmission to achieve $\pm$1m horizontal accuracy; (2) artificial reef platforms for Titan's hydrocarbon seas utilizing specialized sensor arrays and multi-stage communication chains; (3) precision orbital rendezvous techniques demonstrating novel thermal protection solutions; (4) miniaturized CubeSat architectures for asteroid exploration with optimized power-to-mass ratios; and (5) next-generation power management systems for MARS rovers addressing dust accumulation challenges. These innovations represent promising directions for future space exploration technologies, particularly in environments where traditional Earth-based electronic solutions prove inadequate. The interdisciplinary nature of these developments highlights the critical intersection of aerospace engineering, electrical engineering, and planetary science in advancing human exploration capabilities beyond Earth orbit.

astro-ph.IM↗

arXiv2022

Learning with Signatures

In this work we investigate the use of the Signature Transform in the context of Learning. Under this assumption, we advance a supervised framework that potentially provides state-of-the-art classification accuracy with the use of few labels without the need of credit assignment and with minimal or no overfitting. We leverage tools from harmonic analysis by the use of the signature and log-signature, and use as a score function RMSE and MAE Signature and log-signature. We develop a closed-form equation to compute probably good optimal scale factors, as well as the formulation to obtain them by optimization. Techniques of Signal Processing are addressed to further characterize the problem. Classification is performed at the CPU level orders of magnitude faster than other methods. We report results on AFHQ, MNIST and CIFAR10, achieving 100% accuracy on all tasks assuming we can determine at test time which probably good optimal scale factor to use for each category.

cs.CV↗