The rise of LLM-based agents has opened new frontiers in AI applications, yet evaluating these agents remains a complex and underdeveloped area. This survey provides an in-depth overview of the emerging field of LLM agent evaluation, introducing a two-dimensional taxonomy that organizes existing work along (1) evaluation objectives -- what to evaluate, such as agent behavior, capabilities, reliability, and safety -- and (2) evaluation process -- how to evaluate, including interaction modes, datasets and benchmarks, metric computation methods, and tooling. In addition to taxonomy, we highlight enterprise-specific challenges, such as role-based access to data, the need for reliability guarantees, dynamic and long-horizon interactions, and compliance, which are often overlooked in current research. We also identify future research directions, including holistic, more realistic, and scalable evaluation. This work aims to bring clarity to the fragmented landscape of agent evaluation and provide a framework for systematic assessment, enabling researchers and practitioners to evaluate LLM agents for real-world deployment.

Software architecture design is a critical, yet inherently complex and knowledge-intensive phase of software development. It requires deep domain expertise, development experience, architectural knowledge, careful trade-offs among competing quality attributes, and the ability to adapt to evolving requirements. Traditionally, this process is time-consuming and labor-intensive, and relies heavily on architects, often resulting in limited design alternatives, especially under the pressures of agile development. While Large Language Model (LLM)-based agents have shown promising performance across various SE tasks, their application to architecture design remains relatively scarce and requires more exploration, particularly in light of diverse domain knowledge and complex decision-making. To address the challenges, we proposed MAAD (Multi-Agent Architecture Design), an automated framework that employs a knowledge-driven Multi-Agent System (MAS) for architecture design. MAAD orchestrates four specialized agents (i.e., Analyst, Modeler, Designer and Evaluator) to collaboratively interpret requirements specifications and produce architectural blueprints enriched with quality attributes-based evaluation reports. We then evaluated MAAD through a case study and comparative experiments against MetaGPT, a state-of-the-art MAS baseline. Our results show that MAAD's superiority lies in generating comprehensive architectural components and delivering insightful and structured architecture evaluation reports. Feedback from industrial architects across 11 requirements specifications further reinforces MAAD's practical usability. We finally explored the performance of the MAAD framework with three LLMs (GPT-4o, DeepSeek-R1, and Llama 3.3) and found that GPT-4o exhibits better performance in producing architecture design, emphasizing the importance of LLM selection in MAS-driven architecture design.

Despite the rapid expansion of electric vehicle (EV) charging networks, questions remain about their efficiency in meeting the growing needs of EV drivers. Previous simulation-based approaches, which rely on static behavioural rules, have struggled to capture the adaptive behaviours of human drivers. Although reinforcement learning has been introduced in EV simulation studies, its application has primarily focused on optimising fleet operations rather than modelling private drivers who make independent charging decisions. Additionally, long-distance travel remains a primary concern for EV drivers. However, existing simulation studies rarely explore charging behaviour over large geographical scales. To address these gaps, we propose a multi-stage reinforcement learning framework that simulates EV charging demand across large geographical areas. We validate the model against real-world data, and identify the training stage that most closely reflects actual driver behaviour, which captures both the adaptive behaviours and bounded rationality of private drivers. Based on the simulation results, we also identify critical 'charging deserts' where EV drivers consistently have low state of charge. Our findings also highlight recent policy shifts toward expanding rapid charging hubs along motorway corridors and city boundaries to meet the demand from long-distance trips.

The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web, a new phase of the internet defined by autonomous, goal-driven interactions. In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users. This transition from human-driven to machine-to-machine interaction allows intent to be delegated, relieving users from routine digital operations and enabling a more interactive, automated web experience. In this paper, we present a structured framework for understanding and building the Agentic Web. We trace its evolution from the PC and Mobile Web eras and identify the core technological foundations that support this shift. Central to our framework is a conceptual model consisting of three key dimensions: intelligence, interaction, and economics. These dimensions collectively enable the capabilities of AI agents, such as retrieval, recommendation, planning, and collaboration. We analyze the architectural and infrastructural challenges involved in creating scalable agentic systems, including communication protocols, orchestration strategies, and emerging paradigms such as the Agent Attention Economy. We conclude by discussing the potential applications, societal risks, and governance issues posed by agentic systems, and outline research directions for developing open, secure, and intelligent ecosystems shaped by both human intent and autonomous agent behavior. A continuously updated collection of relevant studies for agentic web is available at: https://github.com/SafeRL-Lab/agentic-web.

--Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks. Once such risk is a cascading risk: a breach in one agent can cascade through the system, compromising others by exploiting inter-agent trust. In tandem with OW ASP's initiative for an Agentic AI V ulnerability Scoring System we define an attack vector, Agent Cascading Injection, analogous to Agent Impact Chain and Blast Radius, operating across networks of agents. In an ACI attack, a malicious input or tool exploit injected at one agent leads to cascading compromises and amplified downstream effects across agents that trust its outputs. We formalize this attack with an adversarial goal equation and key variables (compromised agent, injected exploit, polluted observations, etc.), capturing how a localized vulnerability can escalate into system-wide failure. We then analyze ACI's properties - propagation chains, amplification factors, and inter-agent compound effects - and map these to OW ASP's emerging Agentic AI risk categories (e.g. Finally, we argue that ACI highlights a critical need for quantitative benchmarking frameworks to evaluate the security of agent-to-agent communication protocols. We outline a methodology for stress-testing multi-agent systems (using architectures such as Google's A2A and Anthropic's MCP) against cascading trust failures, developing upon groundwork for measurable, standardized agent to agent security evaluation. Our work provides the essential apparatus for engineers to benchmark system resilience, make data-driven architectural trade-offs, and develop robust defenses against a new generation of agentic threats. Index T erms --component, formatting, style, styling, insert. As the use of autonomous AI agents expands across cyber-security, finance, healthcare, and critical infrastructure, agent-to-agent communication protocols have emerged as founda-tional components for coordinating tasks, sharing information, and executing distributed decision-making.

Enterprise environments contain a heterogeneous, rapidly growing collection of internal artifacts related to code, data, and many different tools. Critical information for assessing privacy risk and ensuring regulatory compliance is often embedded across these varied resources, each with their own arcane discovery and extraction techniques. Therefore, large-scale privacy compliance in adherence to governmental regulations requires systems to discern the interconnected nature of diverse artifacts in a common, shared universe. We present Privacy Artifact ConnecT or (PACT), an embeddings-driven graph that links millions of artifacts spanning multiple artifact types generated by a variety of teams and projects. Powered by the state-of-the-art DRAGON embedding model, PACT uses a contrastive learning objective with light fine-tuning to link artifacts via their textual components such as raw metadata, ownership specifics, and compliance context. Experimental results show that PACT's fine-tuned model improves recall@1 from 18% to 53%, the query match rate from 9.6% to 69.7% when paired with a baseline AI agent, and the hitrate@1 from 25.7% to 44.9% for candidate selection in a standard recommender system.

This paper presents a comprehensive refutation of the so-called "blockchain trilemma," a widely cited but formally ungrounded claim asserting an inherent trade-off between decentralisation, security, and scalability in blockchain protocols. Through formal analysis, empirical evidence, and detailed critique of both methodology and terminology, we demonstrate that the trilemma rests on semantic equivocation, misuse of distributed systems theory, and a failure to define operational metrics. Particular focus is placed on the conflation of topological network analogies with protocol-level architecture, the mischaracterisation of Bitcoin's design--including the role of miners, SPV clients, and header-based verification--and the failure to ground claims in complexity-theoretic or adversarial models. By reconstructing Bitcoin as a deterministic, stateless distribution protocol governed by evidentiary trust, we show that scalability is not a trade-off but an engineering outcome. The paper concludes by identifying systemic issues in academic discourse and peer review that have allowed such fallacies to persist, and offers formal criteria for evaluating future claims in blockchain research.

Biased data representation in AI marginalizes up to 75 million autistic people worldwide through medical applications viewing autism as a deficit of neurotypical social skills rather than an aspect of human diversity, and this perspective is grounded in research questioning the humanity of autistic people. Turing defined artificial intelligence as the ability to mimic human communication, and as AI development increasingly focuses on human-like agents, this benchmark remains popular. In contrast, we define Neuro-Inclusive AI as datasets and systems that move away from mimicking humanness as a benchmark for machine intelligence. Then, we explore the origins, prevalence, and impact of anti-autistic biases in current research. Our work finds that 90% of human-like AI agents exclude autistic perspectives, and AI creators continue to believe ethical considerations are beyond the scope of their work. To improve the autistic representation in data, we conduct empirical experiments with annotators and LLMs, finding that binary labeling schemes sufficiently capture the nuances of labeling anti-autistic hate speech. Our benchmark, AUTALIC, can be used to evaluate or fine-tune models, and was developed to serve as a foundation for more neuro-inclusive future work.

Current AI systems rely on opaque reasoning processes that hinder human oversight and collaborative potential. Conventional explainable AI approaches offer post-hoc justifications and often fail to establish genuine symbiotic collaboration. In this paper, the Symbiotic Epistemology is presented as a philosophical foundation for human-AI cognitive partnerships. Unlike frameworks that treat AI as a mere tool or replacement, symbiotic epistemology positions AI as a reasoning partner, fostering calibrated trust by aligning human confidence with AI reliability through explicit reasoning patterns and confidence assessments. SynLang (Symbiotic Syntactic Language) is introduced as a formal protocol for transparent human-AI collaboration. The framework is empirically validated through actual human-AI dialogues demonstrating AI's adaptation to structured reasoning protocols and successful metacognitive intervention. The protocol defines two complementary mechanisms: TRACE for high-level reasoning patterns and TRACE_FE for detailed factor explanations. It also integrates confidence quantification, declarative control over AI behavior, and context inheritance for multi-agent coordination. By structuring communication and embedding confidence-calibrated transparency, SynLang, together with symbiotic epistemology, enables AI systems that enhance human intelligence, preserve human agency, and uphold ethical accountability in collaborative decision-making. Through dual-level transparency, beginning with high-level reasoning patterns and progressing to granular explanations, the protocol facilitates rapid comprehension and supports thorough verification of AI decision-making.

T ext-to-Image (T2I) generative models have revolutionized content creation but remain highly sensitive to prompt phrasing, often requiring users to repeatedly refine prompts multiple times without clear feedback. While techniques such as automatic prompt engineering, controlled text em-beddings, denoising, and multi-turn generation mitigate these issues, they offer limited controllability, or often necessitate additional training, restricting the generalization abilities. Thus, we introduce T2I-Copilot, a training-free multi-agent system that leverages collaboration between (Multimodal) Large Language Models to automate prompt phrasing, model selection, and iterative refinement. This approach significantly simplifies prompt engineering while enhancing generation quality and text-image alignment compared to direct generation. Specifically, T2I-Copilot consists of three agents: (1) Input Interpreter, which parses the input prompt, resolves ambiguities, and generates a standardized report; (2) Generation Engine, which selects the appropriate model from different types of T2I models and organizes visual and textual prompts to initiate generation; and (3) Quality Evaluator, which assesses aesthetic quality and text-image alignment, providing scores and feedback for potential regeneration. T2I-Copilot can operate fully autonomously while also supporting human-in-the-loop intervention for fine-grained control. On GenAI-Bench, using open-source generation models, T2I-Copilot achieves a VQA score comparable to commercial models RecraftV3 and Imagen 3, surpasses FLUX1.1-pro by 6.17% at only 16.59% of its cost, and outperforms FLUX.1-dev and SD 3.5 Large by 9.11% and 6.36%.