Related papers: Architectural Design Decisions in AI Agent Harness…
The agent harness, the system layer comprising prompts, tools, memory, and orchestration logic that surrounds the model, has emerged as the central engineering abstraction for LLMbased agents. Yet harness design remains ad hoc, with no…
Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…
In high-stakes disaster scenarios, timely and informed decision-making is critical yet often challenged by uncertainty, dynamic environments, and limited resources. This paper presents a systematic review of Human-AI collaboration patterns…
Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…
Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after…
Over the past three decades, considerable effort has been devoted to the study of software architecture. A major portion of this effort has focused on the originally proposed view of four "C"s---components, connectors, configurations, and…
Artificial intelligence (AI) in its various forms finds more and more its way into complex distributed systems. For instance, it is used locally, as part of a sensor system, on the edge for low-latency high-performance inference, or in the…
The rapid adoption of AI coding agents and AI assistant web services is fundamentally changing how developers discover, consume, and interact with technical documentation. This paper studies that transformation across three interconnected…
Large Language Models (LLMs) can generate Computer-Aided Design (CAD), yet lack physical comprehension required for reliable engineering design. Instead of attempting to implicitly learn physical laws from data, we propose a Hybrid…
Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens when an agent is embedded persistently in a real academic research environment with durable…
Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct…
We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…
Agentic AI prototypes are being deployed across domains with increasing speed, yet no methodology for their structured design, governance, and prospective evaluation has been established. Existing AI documentation practices and guidelines…
AI agents are assuming active roles in Continuous Integration and Continuous Deployment (CI/CD) workflows, yet the research community lacks a shared vocabulary for describing what it means for CI/CD to be agentic, how much decision…
Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…
Some crucial decisions in AI design tend to be overlooked or factor choices are assumed implicitly. The question often answered first is what the AI will do, not how it will interact with the rest of the world. This reduces our…
The consensus strategies used in collaborative multi-agent systems (MAS) face notable challenges related to adaptability, scalability, and convergence certainties. These approaches, including structured workflows, debate models, and…
Artificial intelligence tools are increasingly embedded in everyday work, yet employees' uptake varies widely even within the same organization. Drawing on sociotechnical and work design perspectives, this research examines whether…
AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates…
Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static…