Search papers

9 results

• PubArx:2026.00009 Artificial Intelligence 8 Nov 2026 Open for review

  GradReason: LLMs as Meta-Learners that Replace Training Epochs with Training-Data-Free Weight Updates

  Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour

  Standard training recipes make a fixed number of passes over the training data, even when an epoch mostly adds mini-batch noise. We study whether a large language model (LLM) that reads the weight and gradient history of a run can replace some of these epochs with updates that compute no gradient and read no training image. In GradReason, an LLM agent is called every ten epochs. In a restricted sandbox it analyses recent weight snapshots, epoch-mean gradients and validation metrics, then submits a Python program that computes new weights and a plan marking each of the next ten epochs as data or virtual. A virtual epoch is kept only if it passes a forward-only check on 5,000 held-out validation images. In 120 runs on CIFAR-10 and CIFAR-100 with three architectures, Claude Opus 5.5 used 32.8\% fewer data epochs than the 80-epoch recipe at 0.31 percentage points lower test accuracy (95\% CI $-0.72$ to $+0.09$; 0.94 points on ResNet-18), on the recipe's own frontier of data against accuracy. Unprompted, Opus averaged recent weight snapshots in every run. This choice produced the savings: a fixed rule with the same acceptance check but extrapolations from prior work saved 5.4\% of the data epochs, and the same rule with averaging added saved 25.0\%. The LLM's contribution is to find a working update within a single run; once found, a fixed rule implements it equally well. An Opus run cost 0.68 USD, but at this scale the agent's latency exceeded the GPU time it saved.

  Abstract PDF
• PubArx:2026.00008 Artificial Intelligence 8 Nov 2026 Open for review

  PIA: Agentic Physics-Informed Runtime Anomaly Detection

  Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour

  Runtime anomaly detectors for cyber-physical systems are either learned as black boxes from normal data, which miss stealthy manipulations that keep every signal inside its normal range, or derived by hand from physical models, which requires expert effort for every plant. We introduce physics-informed agents (PIA), in which a large language model agent writes the detector itself as a set of physical residuals, such as pump characteristics, tank mass balances, and controller logic, and refines every candidate against normal operating data through an evaluation workbench before deployment. The result is a compact, human-readable detector that runs in milliseconds and names the component behind each alarm. On the BATADAL water distribution attack benchmark, PIA with Claude Opus 5.5 reaches an F1 of 0.878 on the test attacks against 0.504 for the strongest of six statistical and deep baselines, keeps detecting attacks concealed by replayed and offset sensor readings, and attributes every detected test attack to the attacked component. Ablations show that testing hypotheses against data is decisive: agents that write residuals from the plant description alone lose up to 0.28 F1, whereas agents that see only anonymized signals recover most of the physical structure.

  Abstract PDF
• PubArx:2026.00007 Artificial Intelligence 6 Nov 2026

  FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning

  Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour

  Federated learning servers combine client models with a fixed aggregation rule, and each rule in common use is designed for one kind of heterogeneity. We study whether a large language model (LLM) that inspects the client models can choose the rule itself, without any training on the server. In FedReason, the LLM is called every ten rounds. It analyses the weights by running code in a restricted server-side sandbox, sees only the printed results, may score a few candidates on a 500-image proxy set, and submits a short Python aggregation program. The server applies the program until the next call and falls back to FedAvg whenever its output is invalid. Full weight tensors never leave the server. We evaluated FedReason with Claude Opus 5.5 on CIFAR-10 and CIFAR-100 with ResNet-18 under Dirichlet label skew, width-heterogeneous sub-models and Byzantine clients, in 168 runs against 14 baselines. Across 12 paired label-skew runs it beat FedAvg by 1.26 percentage points on average (10 wins), and a control that spends the same per-round proxy budget on choosing among standard rules by 1.08 points. It was the strongest server-side rule on CIFAR-100 but did not beat SCAFFOLD, which changes client training. With three of ten clients malicious, it excluded all sign-flipping clients from the first round and stayed about one point below FLTrust without training a root model. Without proxy feedback, accuracy fell from 73.8\% to 38.8\% in one seed. A 60-round run cost 0.79 USD in API fees on average.

  Abstract PDF
• PubArx:2026.00006 Artificial Intelligence 4 Nov 2026 Thesis or dissertation chapter

  Multi-Agent Daily Planning System (MADPS): A GAIA-Based Architecture for Dynamic Scheduling

  Shuvam Agarwala, Ali Mohammadi Ruzbahani

  This document outlines the GAIA methodology design for a single-user Multi-Agent Daily Planning System (MADPS) engineered to generate, adapt, and personalize daily schedules. The architecture consists of three core autonomous components: the User Profile Agent (UPA), the Task Management Agent (TMA), and the Planning & Adaptation Agent (PAA). MADPS is designed to maximize priority satisfaction under constraints, minimize re-planning latency and schedule churn during task disruptions, and personalize schedules by learning user energy curves and preference weights. To support these objectives, the system employs FIPA-style interaction protocols and a dual-strategy PAA workflow, utilizing rapid, greedy local repairs for minor schedule disruptions and Genetic Algorithm (GA)-driven global optimization for system-wide impacts. Proposed schedules are evaluated using a comprehensive fitness function that carefully weights priority satisfaction, energy alignment, transition minimization, and hard constraint penalties to ensure feasible and highly optimized daily plans.

  Abstract PDF
• PubArx:2026.00005 Software Engineering 4 Nov 2026 Thesis or dissertation chapter

  Smart Contracts as Autonomous Agents: Engineering a Decentralized Naming Infrastructure on the Polygon Blockchain

  Shuvam Agarwala, Ali Mohammadi Ruzbahani

  While traditional multi-agent system (MAS) frameworks such as JADE and SPADE rely on distributed computing environments and asynchronous message passing, "Report-2.pdf" presents a novel paradigm: deploying blockchain smart contracts as fully autonomous agents. This detailed development document chronicles the implementation of the University of Calgary Name Service (UCNS) on the Polygon network, systematically translating abstract GAIA architectural designs into executable Solidity code. The specification provides a comprehensive engineering blueprint, encompassing detailed use case specifications, UML class and sequence diagrams modeling trustless inter-agent protocols, and explicit entity-relationship data structures. By detailing Web3 frontend integration, rigorous testing strategies, and mainnet deployment procedures, this report demonstrates how transaction-based coordination effectively replaces centralized platform mediation. The resulting implementation validates the application of agent-oriented software engineering principles to build secure, immutable, and production-ready decentralized applications

  Abstract PDF
• PubArx:2026.00004 Software Engineering 4 Nov 2026 Thesis or dissertation chapter

  Decentralized Naming Services on Polygon: A GAIA-Based Multi-Agent System Design

  Shuvam Agarwala, Ali Mohammadi Ruzbahani

  This document applies the Generic Architecture for Information Availability (GAIA) methodology to design the University of Calgary Name Service (UCNS), a decentralized naming infrastructure operating on the Polygon blockchain. By methodically progressing through GAIA’s requirements analysis, architectural design, and detailed design phases, the report translates high-level operational goals into a structured multi-agent system. The design specifies three distinct roles—Registry Manager, Resolution Provider, and Pricing Authority—and maps them to three singleton smart contract agents: the Registry Agent, Resolver Agent, and Pricing Agent. Detailed specifications for internal agent state, inter-agent communication protocols (e.g., domain registration and ownership transfer), and service implementations are provided to ensure trustless, decentralized coordination. Ultimately, this architectural blueprint bridges theoretical agent-oriented software engineering with practical Web3 implementation, demonstrating the efficacy of GAIA in designing robust, modular blockchain applications.

  Abstract PDF
• PubArx:2026.00003 Software Engineering 4 Nov 2026 Thesis or dissertation chapter

  Architecting Decentralized Identity: An Agent-Oriented Naming Infrastructure on the Polygon Blockchain

  Shuvam Agarwala, Ali Mohammadi Ruzbahani

  Traditional blockchain naming systems typically rely on monolithic smart contracts that couple logic tightly, limiting component isolation, independent upgradeability, and clear behavioral reasoning. As detailed in "Report-1A-System-Specification.pdf", the University of Calgary Name Service (UCNS) overcomes these limitations through a fully decentralized, agent-based naming infrastructure deployed on the Polygon network. By applying agent-oriented software engineering principles to a Web3 environment, UCNS decomposes system architecture into three autonomous smart contract entities: a Registry Agent, a Resolver Agent, and a Pricing Agent. These independent agents operate without centralized control, coordinating seamlessly through structured message-passing to execute domain registration, lifecycle ownership management, dynamic pricing, and address resolution. This modular separation of concerns ensures verifiable ownership, tamper-proof state maintenance, and transparent on-chain computation while establishing a robust foundation for multi-agent systems in decentralized applications. Ultimately, this specification demonstrates the viability of specialized autonomous agents in replacing monolithic paradigms for practical, production-grade blockchain identity management.

  Abstract PDF
• PubArx:2026.00002 Cryptography and Security 4 Nov 2026

  Gather or Act? Belief-Level Counterfactual Labels for Deadline-Aware Incident Response in Cyber-Physical Systems

  Ali Mohammadi Ruzbahani

  When an industrial control system misbehaves, the defender often must choose between acting now on the most likely cause and first gathering evidence that separates two look-alike causes, while the process drifts toward a shutdown. Learning or evaluating such decisions requires the cost of every candidate action from the same situation, which no public cyber-physical security dataset provides. We present TE-GvA, a counterfactual decision dataset for fault-driven incident response on the revised Tennessee Eastman process, with 9,908 decision points from 1,990 simulated incidents, each with 4 to 35 candidate actions labelled by branched rollouts with common random numbers. Labels computed under the true hidden cause (hindsight labels) make gathering the best choice in only 1.1-1.3% of decisions. For the dominant look-alike pair, a failed network link versus a frozen I/O module, we add pair-conditioned belief labels from twin episodes that replay the defender's history under the other cause, weighted by the exact posterior. With them, gathering is best in 15.5% of ambiguous natural decisions and in 33.1% of ambiguous stress decisions without a backup channel. When the posterior is correct and the twin is faithful, belief labels have the same regression target as hindsight labels and lower variance. In a pre-specified, single-look test evaluation, a gradient-boosted rule trained on belief labels has 11% lower regret on the stress set than the same rule trained on hindsight labels, and 27% lower regret on ambiguous stress decisions without a backup channel, which remains significant after Holm correction. With a backup channel and in the natural distribution, the two label sets perform about the same. Soft labels tolerate moderate posterior errors, whereas hard labels that commit to one cause do worse than hindsight labels.

  Abstract PDF
• PubArx:2026.00001 Artificial Intelligence 29 Oct 2026 Review article

  Decentralizing Cybersecurity across Artificial Intelligence, Internet of Things, Blockchain, Machine Learning, and Agentic AI: A Systematic Literature Review

  Rezvan Abouzadeh

  Cybersecurity was built around a perimeter, a trusted central server, and a human analyst who reads the alerts. None of the three holds up well in deployments where billions of constrained devices generate data at the edge, models are trained across organizational borders, ledgers record who did what, and autonomous software agents act at machine speed on behalf of people. This article reviews how decentralization is being used to respond to that shift. We code and synthesize 216 studies, 94 of them drawn from one research programme on federated, blockchain-based, and autonomous defence and 122 from the wider literature on mechanisms, attacks, and standards, across five technology families: the Internet of Things, machine learning, federated and other decentralized learning, blockchain, and agentic artificial intelligence. Four findings stand out. Decentralized learning is the most mature of the strands and now has a credible answer to poisoning and inference threats, though at a cost in complexity that few papers measure. Blockchains contribute auditability and identity more reliably than they contribute detection. Agentic AI is the least settled strand, with evidence of attack running well ahead of evidence of defence. And very few studies combine more than two families, so the integrated architectures the field keeps proposing are mostly untested. We distil three reusable algorithms and a layered reference architecture, and we close with a research agenda built around accountability, evaluation, and post-quantum readiness.

  Abstract PDF