Automated surveillance of arXiv for my core research tracks.
Scope: Intersection of Large Language Models (LLM) and ICS/SCADA.
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed number of iterations. We argue that practical optimization should maximize...
Policy-gradient methods are central to modern reinforcement learning, including LLM post-training. When they struggle, the usual suspects are exploration, credit assignment and action-sampling noise. Classification has none of them. A classifier is a policy whose expected reward, its \emph{expected accuracy},...
Large language models (LLMs) are increasingly used to support legal practice, education, and research, yet their reliability in national legal systems outside the United States remains largely undocumented. We introduce an expert-validated benchmark for evaluating LLM reliability on the Colombian...
Designing a scientific instrument tests whether language-model agents can do physics rather than recall it, provided the grading cannot be argued with. We introduce NeutronGym, to our knowledge the first executable environment for neutron instrument design: agents build instruments through...
The construction industry faces persistent labor shortages, low productivity that costs the global economy over $1.6 trillion annually, and one of the highest injury rates among major industries. These factors motivate the use of autonomous robots to improve efficiency and...
Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense mechanisms, assuming that they describe the security of the agent. In this...
We describe the Writerslogic team's participation in the CLEF 2026 SimpleText shared task, addressing Task 1 (text simplification) and Task 2 (complexity spotting). For Task 1, we develop a multi-candidate generation pipeline using GPT-4o-mini that produces five simplification candidates per...
Large language models (LLMs) have reached expert-level performance on competition mathematics largely through the volume of search placed around them: candidate solutions are sampled in quantity and retained only when an external criterion accepts them. Such a procedure improves the...
Authorship Attribution (AA) requires capturing fine-grained stylistic characteristics, making it particularly challenging in zero-shot (ZS) settings where no task-specific supervision is available. In this work, we investigate the effect of author representations on ZS AA by evaluating a label-only prompting...
Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential capability for automated data science and decision support. Its central challenge lies in systematically discovering verifiable com- posite insights across...
General-purpose Text-to-SQL systems achieve strong performance on academic benchmarks like Spider and BIRD, where schemas are relatively shallow and column values are often human readable. In production financial databases, where concepts are stored as opaque integer keys rather than human-readable...
Static-analysis scanners can identify personal-data types in source code, but they lack mechanisms to connect these findings to standardized privacy vocabularies. PrivDev maps 122 Bearer CLI data types to Data Privacy Vocabulary Personal Data (DPV-PD) categories and links them to...
Recent advances in autoregressive video generation have improved temporal consistency over extended durations, yet interactive storytelling requires more than continuous scene extension: a new shot may combine characters and backgrounds from different historical shots. Whole prompt retrieval can overlook the...
Hallucination detection is particularly important for medical language models, but repeated-sampling approaches are expensive and existing uncertainty-head resources do not directly transfer to a new backbone and language. We adapt the LLM Uncertainty Head (LUH) framework to Aya-Expanse-8B-based Persian medical...
Post-training a large language model (LLM) often requires exploring trade-offs between multiple rewards, but retraining for each trade-off is expensive. Decoding-time policy composition allows these trade-offs to be adjusted by combining reward-specific policies at inference time. This composition targets a...
Post-training with verifiable rewards can induce reward hacking, motivating the use of monitors within the training objective rather than solely for offline auditing. We show that a low monitor readout does not identify whether such an intervention controls behavior. In...
Academic compute is fragmented: allocations are granted per facility, and facilities differ in accelerators and software stacks, schedule jobs independently, and share neither a network nor a filesystem. We present a system that pools such allocations to pre-train a single...
LLM agents increasingly screen tool outputs with small prompt-injection detectors, and teams choose among detectors by their scores on public benchmarks. We ask whether those scores predict how a detector behaves inside an agent. We replay the ground-truth tool calls...
A targeted adversarial perturbation can drive a vision-language model's (VLM's) teacher-forced training loss for a fixed target caption to near zero, yet the same model, allowed to generate freely, produces the original, correct description with no trace of the target....
Large language model-based agents are increasingly deployed to perform domain-specific tasks by interacting with enterprise knowledge, tools, and external services. Existing runtime guardrails primarily target prompt injection and other attack-specific behaviors under a black-box threat model, but provide limited guarantees...
Scope: AI Governance, Policy as Code, and Compliance Engineering.
Artificial intelligence governance exhibits a striking paradox: while major jurisdictions converge rhetorically around concepts such as safety, risk, and accountability, their regulatory frameworks remain fundamentally divergent and mutually unintelligible. This paper argues that this fragmentation cannot be explained solely by...
The EU AI Act adopts a horizontal and adaptive approach to govern AI technologies characterised by rapid development and unpredictable emerging capabilities. To maintain relevance, the Act embeds provisions for regulatory learning. However, these provisions operate within a complex network...
This essay examines the evolving concept of legal personality through the lens of recent developments in artificial intelligence and the possible emergence of superintelligence. Legal systems have long been open to extending personhood to non-human entities, most prominently corporations, for...
Trust and Reputation Management Systems (TRMSs) are critical for the modern web, yet their reliance on subjective user ratings or narrow Quality of Service (QoS) metrics lacks objective grounding. Concurrently, while regulatory frameworks like GDPR and HIPAA provide objective behavioral...
Current DAO governance praxis limits organizational expressivity and reduces complex organizational decisions to token-weighted voting due to on-chain computational limits. This paper proposes verifiable off-chain computation (leveraging Verifiable Services, TEEs, and ZK proofs) as a framework to transcend these constraints...
Natural Language Processing (NLP) systems are increasingly used in sensitive domains such as healthcare, finance, and government, where they handle large volumes of personal and regulated data. However, these systems introduce distinct risks related to security, privacy, and regulatory compliance...
Agentic AI systems present both significant opportunities and novel risks due to their capacity for autonomous action, encompassing tasks such as code execution, internet interaction, and file modification. This poses considerable challenges for effective organizational governance, particularly in comprehensively identifying,...
Large Language Models (LLMs) and AI chatbots are increasingly used for emotional and mental health support due to their low cost, immediacy, and accessibility. However, when safety guardrails are triggered, conversations may be abruptly terminated, introducing a distinct form of...
This paper tackles practical challenges in governing child centered artificial intelligence: policy texts state principles and requirements but often lack reproducible evidence anchors, explicit causal pathways, executable governance toolchains, and computable audit metrics. We propose Graph-GAP, a methodology that decomposes...
This policy memo examines the evolution of the international AI Summit series, initiated at Bletchley Park in 2023 and continued through Seoul in 2024 and Paris in 2025, as a forum for cooperation on the governance of advanced artificial intelligence....
Over a billion users across the globe interact with AI systems engineered with increasing sophistication to mimic human traits. This shift has triggered urgent debate regarding Anthropomorphism, the attribution of human characteristics to synthetic agents, and its potential to induce...
Artificial intelligence systems are increasingly deployed in domains that shape human behaviour, institutional decision-making, and societal outcomes. Existing responsible AI and governance efforts provide important normative principles but often lack enforceable engineering mechanisms that operate throughout the system lifecycle. This...
Growing concerns about fairness, privacy, robustness, and transparency have made it a central expectation of AI governance that automated decisions be explainable by institutions and intelligible to affected parties. We introduce the Smart Data Portfolio (SDP) framework, which treats data...
The rapid advancements in artificial intelligence (AI) present unique challenges for policymakers that seek to govern the technology. In this context, the Delphi method has become an established way to identify consensus and disagreement on emerging technological issues among experts...
Frontier AI developers operate at the intersection of rapid technical progress, extreme risk exposure, and growing regulatory scrutiny. While a range of external evaluations and safety frameworks have emerged, comparatively little attention has been paid to how internal organizational assurance...