Danial Hameed

Municipalities increasingly delegate healthcare, social assistance, utilities, transit, and identity verification to semi-autonomous systems. Real-world failures, including Australia's Robodebt scheme and the Dutch childcare benefits scandal, show that automated administration can strip life-sustaining services from large populations whose formal entitlements never changed. Existing governance responses remain fragmented across sectoral silos, with none enforcing a computationally verified constraint at the individual level across multiple domains concurrently. We present \HSC{}, a multi-agent framework that operationalizes essential human functioning as a non-compensatory constraint on automated municipal allocation. The architecture establishes a per-resident capability floor over ten normalized dimensions, identifying deprivation via an Alkire--Foster dual cutoff so that surplus in one domain cannot offset deficits in another. A Human Sovereignty Gate evaluates candidate allocations by measured worst-case capability impact and reversibility, recording commitments in an auditable ledger for which we prove that no admissible sequence of automated decisions can cross the floor. A Basic Needs Assurance Engine coordinates sector agents over a cyclic dependency graph to block cross-sector cascades, backed by an offline resilience reserve during platform outages. We derive a feasibility bound showing that individual risk tolerance cannot be legislated to zero, and specify an agent-based evaluation protocol for 250{,}000 synthetic residents across six disruption scenarios.

Recent advances in large language models and multimodal foundation models have enabled artificial intelligence agents to jointly process text, images, and other modalities while performing multi-step reasoning and interacting with external tools. Despite this progress, autonomous agents remain prone to compounding errors that originate in visual perception, language reasoning, tool invocation, or the interaction among these components. This paper proposes a self-correcting multimodal agent architecture that couples task decomposition and planning with an explicit verification and revision loop, allowing the agent to detect inconsistencies in intermediate reasoning steps and in final outputs before a task is considered complete. The architecture combines cross-modal evidence aggregation, secondary-model critique, rule-based consistency checks, and tool-grounded verification to identifycandidate errors, and it uses a bounded iterative revision procedure to correct them without unnecessary recomputation. We formalize the verification-and-correction process as a constrained optimization over an evolving action-reasoning trace and describe a concrete algorithmic instantiation suitable for visual question answering, document understanding, and tool-augmented reasoning tasks. We further describe an evaluation protocol spanning accuracy, factual reliability, task completion, and robustness to injected multimodal errors, together with an explicit accounting of the additional inference-time cost introduced by iterative self-correction. The framework is intended to give practitioners a concrete, reproducible template for building and evaluating multimodal agents that can detect and recover from their own mistakes prior to acting autonomously.

Cities face pressure from urban growth and climate risk, yet deployed systems stay single-domain and reactive. This PRISMA-guided rapid review applies operationalized criteria to separate Agentic AI from conventional machine learning for SDG 11 (Sustainable Cities and Communities) and SDG 13 (Climate Action). Agentic AI is defined by four properties: task-level autonomy, goal-directed planning, tool use, and multi-agent coordination; evidencing at least two marks a system as fully agentic. A two-tier search across five databases with backward citation tracking returned 896 records (2018–2026), of which 60 met the eligibility criteria and 14 satisfied the agentic threshold. The corpus is stratified by study type with a threshold sensitivity analysis. Two contributions follow: a reference architecture specifying how an agentic layer and an urban digital twin exchange state, and a real-data feasibility study on the SEVIR archive testing whether multimodal fusion improves hazard classification. On real data the proposed model is the best-ranked of four but only marginally exceeds a no-change persistence baseline, giving the assumption weak support, not operational evidence. The review reveals a field growing sharply since 2023, clustered in a few urban and climate domains, with almost no validated cross-domain deployment.

Artificial intelligence is transforming assistive technologies, yet many systems remain reactive, fragmented, and insufficiently personalized for individuals with disabilities and neurodivergent conditions. This chapter examines the architectural, design, and governance foundations of trustworthy agentic assistive systems. It synthesizes limitations of conventional approaches, including restricted adaptability, low interoperability, and weak support for user autonomy, and introduces a taxonomy of agentic architectures to guide scalable deployment. The chapter proposes a multi-agent framework integrating multimodal interaction, hybrid reasoning, explainable AI, and health-aware data to enable context-sensitive support. It further addresses privacy, ethical governance, and responsible institutional adoption while outlining future research directions. By bridging architectural innovation with human-centered design, this work advances a forward-looking vision for inclusive intelligent environments.

Rapid urbanization and intensifying climate risks are placing unprecedented pressure on cities to transition toward sustainable and resilient models. Achieving Sustainable Development Goals (SDGs) 11 (Sustainable Cities and Communities) and 13 (Climate Action) requires intelligent systems capable of interpreting complex urban dynamics and enabling proactive, adaptive decision-making. This paper presents a PRISMA-guided rapid review examining the role of Agentic Artificial Intelligence (AAI)–autonomous, goal-directed systems with multi-step reasoning, tool use, and multi-agent coordination–in advancing urban sustainability and climate resilience. Studies were required to exhibit at least two attributes: autonomous decision-making, multi-step planning, tool use or environmental interaction, and multi-agent coordination. From 920 records, 70 peer-reviewed studies were synthesized, covering smart mobility, infrastructure planning, waste management, emergency response, climate monitoring, emissions tracking, renewable energy forecasting, and multi-hazard early warning systems. Results show that despite rapid progress, AAI applications remain fragmented and domain-specific. To address this, a unified Agentic AI–Digital Twin framework is proposed, integrating real-time sensing, urban–climate co-simulation, multi-agent coordination, and adaptive decision intelligence. A Pareto-based optimization approach balances competing sustainability goals. Key challenges in interoperability, data governance, ethics, and scalability are identified, alongside a research roadmap for integrated intelligent urban ecosystems.