February 2026

arXiv:2602.17838v1 Announce Type: new Abstract: As developers increasingly rely on LLM-generated code summaries for documentation, testing, and review, it is important to study whether these summaries accurately reflect what the program actually does. LLMs often produce confident descriptions of what the code looks like it should do (intent), while missing subtle edge cases or logic changes that define what it actually does (behavior). We present a mutation-based evaluation methodology that directly tests whether a summary truly matches the […]

Ver mais

arXiv:2602.17837v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks (BFAs), which exploit computer main memory (i.e., DRAM) vulnerabilities to flip a small number of bits in model weights, can severely disrupt LLM behavior. However, existing BFA on LLM largely induce un-targeted failure or general performance degradation, offering limited control over manipulating […]

Ver mais

arXiv:2602.17835v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model’s downstream performance. Gradient-based data selection methods such as TracIn and Influence Functions leverage influence to identify useful samples, but their computational cost scales poorly, making them impractical for multi-billion-parameter large language models (LLMs). A common alternative is to use off-the-shelf smaller models as proxies, but they remain suboptimal since their learning dynamics are unclear, their sizes cannot be flexibly […]

Ver mais

arXiv:2602.17834v1 Announce Type: new Abstract: In the last decade, subgraph detection and enumeration have emerged as a central problem in distributed graph algorithms. This is largely due to the theoretical challenges and practical applications of these problems. In this paper, we initiate the systematic study of distributed sub-hypergraph enumeration in hypergraphs. To this end, we (1)~introduce several computational models for hypergraphs that generalize the CONGEST model for graphs and evaluate their relative computational power, (2)~devise algorithms for distributed […]

Ver mais

arXiv:2602.17832v1 Announce Type: new Abstract: Stochastic Optimal Control provides a unified mathematical framework for solving complex decision-making problems, encompassing paradigms such as maximum entropy reinforcement learning(RL) and imitation learning(IL). However, conventional parametric policies often struggle to represent the multi-modality of the solutions. Though diffusion-based policies are aimed at recovering the multi-modality, they lack an explicit probability density, which complicates policy-gradient optimization. To bridge this gap, we propose MePoly, a novel policy parameterization based on polynomial energy-based models. MePoly […]

Ver mais

arXiv:2602.17831v1 Announce Type: new Abstract: Evaluating the reasoning capabilities of Large Language Models is increasingly challenging as models improve. Human curation of hard questions is highly expensive, especially in recent benchmarks using PhD-level domain knowledge to challenge the most capable models. Even then, there is always a concern about whether these questions test genuine reasoning or if similar problems have been seen during training. Here, we take inspiration from 16th-century mathematical duels to design The Token Games (TTG): […]

Ver mais

arXiv:2602.17829v1 Announce Type: new Abstract: Inferring causal relations in timeseries data with delayed effects is a fundamental challenge, especially when the underlying system exhibits complex dynamics that cannot be captured by simple functional mappings. Traditional approaches often fail to produce generalized and interpretable explanations, as multiple distinct input trajectories may yield nearly indistinguishable outputs. In this work, we present ruleXplain, a framework that leverages Large Language Models (LLMs) to extract formal explanations for input-output relations in simulation-driven dynamical […]

Ver mais

arXiv:2602.17826v1 Announce Type: new Abstract: Language models exhibit fundamental limitations — hallucination, brittleness, and lack of formal grounding — that are particularly problematic in high-stakes specialist fields requiring verifiable reasoning. I investigate whether formal domain ontologies can enhance language model reliability through retrieval-augmented generation. Using mathematics as proof of concept, I implement a neuro-symbolic pipeline leveraging the OpenMath ontology with hybrid retrieval and cross-encoder reranking to inject relevant definitions into model prompts. Evaluation on the MATH benchmark with […]

Ver mais

arXiv:2602.17822v1 Announce Type: new Abstract: Industrial robotics has established itself as an integral component of large-scale manufacturing enterprises. Simultaneously, collaborative robotics is gaining prominence, introducing novel paradigms of human-machine interaction. These advancements have necessitated a comprehensive revision of safety standards, specifically incorporating requirements for cybersecurity and protection against unauthorized access in networked robotic systems. This article presents a comparative analysis of the ISO 10218:2011 and ISO 10218:2025 standards, examining the evolution of their structure, terminology, technical requirements, and […]

Ver mais

arXiv:2602.17819v1 Announce Type: new Abstract: We present a variational optimization approach for the solution of a coefficient inverse problem of simultaneous reconstruction of the dielectric permittivity and conductivity functions in time-dependent Maxwell’s system using limited boundary observations of the electric field. The variational optimization approach is based on constructing a weak form of a Lagrangian which allows to use finite element based reconstruction algorithms. The optimality conditions for the Lagrangian and stability estimate for the adjoint problem are […]

Ver mais