arXiv:2604.06148v1 Announce Type: cross
Abstract: The governance of artificial intelligence has a blind spot: the machine identities that AI systems use to act. AI agents, service accounts, API tokens, and automated workflows now outnumber human ident…
arXiv:2505.00472v2 Announce Type: replace
Abstract: Agentic Artificial Intelligence (AI) constitutes a transformative paradigm in the evolution of intelligent agents and decision-support systems, redefining smart environments by enhancing operational …
arXiv:2604.05080v1 Announce Type: cross
Abstract: We present Nidus, a governance runtime that mechanizes the V-model for AI-assisted software delivery. In the self-hosting deployment, three LLM families (Claude, Gemini, Codex) delivered a 100,000-line…
arXiv:2604.04503v2 Announce Type: replace
Abstract: Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are essential for efficient reasoning and autonomous evol…
arXiv:2604.05278v1 Announce Type: cross
Abstract: Spec-driven development (SDD) with AI coding agents provides a structured workflow, but agents often remain “context blind” in large, evolving repositories, leading to hallucinated APIs and architectur…
arXiv:2601.05905v2 Announce Type: replace-cross
Abstract: As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual p…
arXiv:2602.06934v3 Announce Type: replace-cross
Abstract: Grassroots Logic Programs (GLP) is a multiagent, concurrent, logic programming language designed for the implementation of smartphone-based, serverless, grassroots platforms. Here, we start fro…
arXiv:2604.06091v1 Announce Type: cross
Abstract: Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates diverse peer perspectives to make a final decision. Dra…
arXiv:2604.05018v1 Announce Type: new
Abstract: Synthesizing unstructured research materials into manuscripts is an essential yet under-explored challenge in AI-driven scientific discovery. Existing autonomous writers are rigidly coupled to specific e…
arXiv:2604.05229v1 Announce Type: new
Abstract: Agentic AI systems plan, use tools, maintain state, and produce multi-step trajectories with external effects. Those properties create a governance problem that differs materially from single-turn genera…