The paper discusses how the shift from centralized AI APIs to local edge inference enables Client‑Side Autonomous Agents (CSAAs) that collaborate in Agentic Peer‑to‑Peer (P2P) networks. Unlike traditional P2P systems that exchange static content, these networks share dynamic, heterogeneous capabilities that may be unsafe, necessitating semantic discovery, drift management, and risk‑aware execution. The authors propose a plane‑based reference architecture, signed soft‑state capability descriptors for intent‑aware routing, and a tiered verification spectrum (reputation, canary probes, cryptographic evidence) to align trust costs with task risks, showing improved workflow success in simulations.
arXiv:2606. 17368v1 Announce Type: new Abstract: Large language models have accelerated the transition from passive conversational assistants to autonomous agents that can understand goals, plan actions, invoke tools, and execute multi-step tasks.
arXiv:2608. 03499v1 Announce Type: new Abstract: Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations.
GatewayBench is a new evaluation framework that systematically studies how the design of Model Context Protocol (MCP) gateways influences AI agent capability, efficiency, and security. It categorizes gateways into flattened and hierarchical architectures and tests them on 524 tasks across six domains using a pool of 11,118 real-world tools from 251 MCP servers, including task-irrelevant tools to simulate large-scale deployments. Experiments on seven widely deployed gateways reveal significant differences in task completion, tool-use efficiency, and attack resilience, showing strong interactions with the underlying model and agent harness.
Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners.
AgentKernel proposes a trust‑native operating system for AI agents, arguing that current governance layers are insufficient because they share the same process trust boundary as the agents. The OS introduces a mandatory enforcement boundary organized into four pillars—Identity, Perception, Cognition, and Execution—each adapting classical OS security principles to address semantic‑level failures such as prompt injection, memory poisoning, and tool misuse. By wrapping the agent lifecycle in this structured, non‑bypassable framework, AgentKernel aims to provide a unified security layer that can enforce identity, input mediation, memory governance, and execution control across the entire agent lifecycle.
The paper introduces NetArtifactBench, a benchmark designed to evaluate whether AI agents can detect and repair inconsistencies in network experiment records while preserving supported claims. It tests 23 agent configurations on 52 instances with injected inconsistencies, finding an average pass rate of 65.3 % but no runtime exceeding 30 % for complex repairs that require recovering implicit relations and propagating changes across artifacts. The results highlight a clear distinction between local corrections and full record-level repair, leading the authors to argue that artifact integrity should be a primary design and evaluation criterion for AI agents in network systems.
The paper proposes a scalable trust discovery architecture for the Internet of Agents, featuring a three‑layer hierarchical design: Agent Root for registry governance, Agent Registry for registration and metadata, and Agent Resolver for capability discovery. It introduces a registry‑suffix‑anchored composite identity scheme and a dual‑certificate, multi‑level authentication mechanism to strengthen agent identity trust. Prototype evaluation shows low latency (58 ms registration, 25 ms discovery) and high throughput (over 19,000 registrations and 29,000 discoveries per second).
arXiv:2607. 22611v1 Announce Type: new Abstract: The deployment of autonomous AI agents in production infrastructure introduces fundamental security challenges that traditional role-based access control (RBAC) models cannot address.
arXiv:2606. 09122v1 Announce Type: cross Abstract: Cloud network infrastructure at hyperscale presents unique operational challenges where traditional human-driven incident response cannot keep pace with the volume, velocity, and complexity of failures.
arXiv:2606. 03557v1 Announce Type: new Abstract: As generative AI capabilities expand, AI-driven virtual worlds face a growing architectural challenge.
arXiv:2606. 12835v1 Announce Type: cross Abstract: The rapid emergence of autonomous AI agents is transforming artificial intelligence from isolated model inference into distributed systems of reasoning, communication, and action.
arXiv:2609.06835v1 Announce Type: cross Abstract: Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these s...