Upgrade or Switch: Do We Need a Next-Gen Trusted Architecture for the Internet of AI Agents?

• URL: http://arxiv.org/abs/2506.12003v2
• Date: Fri, 11 Jul 2025 17:44:32 GMT
• Title: Upgrade or Switch: Do We Need a Next-Gen Trusted Architecture for the Internet of AI Agents?
• Abstract summary: The emerging Internet of AI Agents challenges existing web infrastructure designed for human-scale, reactive interactions.<n>This paper analyzes whether to upgrade existing infrastructure or implement purpose-built index architectures for autonomous agents.
• Score: 12.116270471408216
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The emerging Internet of AI Agents challenges existing web infrastructure designed for human-scale, reactive interactions. Unlike traditional web resources, autonomous AI agents initiate actions, maintain persistent state, spawn sub-agents, and negotiate directly with peers: demanding millisecond-level discovery, instant credential revocation, and cryptographic behavioral proofs that exceed current DNS/PKI capabilities. This paper analyzes whether to upgrade existing infrastructure or implement purpose-built index architectures for autonomous agents. We identify critical failure points: DNS propagation (24-48 hours vs. required milliseconds), certificate revocation unable to scale to trillions of entities, and IPv4/IPv6 addressing inadequate for agent-scale routing. We evaluate three approaches: (1) Upgrade paths, (2) Switch options, (3) Hybrid index/registries. Drawing parallels to dialup-to-broadband transitions, we find that agent requirements constitute qualitative, and not incremental, changes. While upgrades offer compatibility and faster deployment, clean-slate solutions provide better performance but require longer for adoption. Our analysis suggests hybrid approaches will emerge, with centralized indexes for critical agents and federated meshes for specialized use cases.

Related papers

• AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities [55.23913617185508]
  Agent is an open-source, lightweight, and infrastructure for evaluating Large Language Models (LLMs)-based agents.<n>It organizes the evaluation process around three independent components, namely Benchmark, Harness and Environment.<n>It features a fault-tolerant runtime and comprehensive trajectory analysis tools to transparently diagnose failure modes like reward-hacking.
  arXiv  Detail & Related papers  (2026-07-15T11:11:17Z)
• The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development? [80.24951682268332]
  We introduce the Meta-Agent Challenge (MAC), an evaluation framework designed to test the capacity of frontier models for autonomous agent development.<n>To ensure evaluation integrity, this framework is secured by multi-layer defenses against reward hacking.<n>We demonstrate that meta-agents rarely match human-engineered baseline policies, and the few that do are dominated by proprietary frontier models.
  arXiv  Detail & Related papers  (2026-06-03T04:58:17Z)
• TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems [55.81570336226014]
  We introduce TacoMAS, a test-time co-evolution framework for dynamic multi-agent systems.<n>TacoMAS formulates MAS inference as a task of online graph adaptation, where nodes represent agents with role-specific capabilities and edges define their communication topology.<n>Experiments on four benchmarks demonstrate that TacoMAS outperforms nearly 20 multi-agent baselines, achieving an average improvement of 13.3% over the strongest baseline.
  arXiv  Detail & Related papers  (2026-05-10T13:52:00Z)
• Infrastructure for the Agentic Web: Gap Analysis and Architecture from the Agentverse Platform [0.0]
  We conduct an empirical audit of the Agentverse platform and characterise what is operational, partially deployed, or absent.<n>We propose a seven-layer Agent Cloud Stack -- a reference architecture for what a fully realised agent-native cloud should provide by 2030.
  arXiv  Detail & Related papers  (2026-04-26T09:26:57Z)
• AI Tool Discovery at Scale: All You Need is DNS [13.956883631679121]
  ToolDNS is a radical framework that retrofits semantic tool discovery onto the Internet's most resilient substrate: the Domain Name System.<n>By embedding functional intent and organizational trust into a hierarchical, ToolDNS transforms an expensive semantic search into a series of lightweight, O(log N) name resolutions.<n>Our work demonstrates that scalable AI interoperability requires not more, but a smarter utilization of the infrastructure already beneath our feet.
  arXiv  Detail & Related papers  (2026-04-19T04:31:19Z)
• AgentGate: A Lightweight Structured Routing Engine for the Internet of Agents [25.130481441368207]
  We present AgentGate, a lightweight structured routing engine for candidate-aware agent dispatch.<n>Instead of treating routing as unrestricted text generation, AgentGate decomposes it into two stages: action decision and structural grounding.<n>Experiments show that compact models can provide competitive routing performance in constrained settings.
  arXiv  Detail & Related papers  (2026-04-08T05:22:16Z)
• Agent Identity URI Scheme: Topology-Independent Naming and Capability-Based Discovery for Multi-Agent Systems [0.0]
  Multi-agent systems face a fundamental architectural flaw: agent identity is bound to network location.<n>We propose the agent:// scheme, which decouples identity from topology through three components.<n>Trust root establishing organizational authority, a hierarchical capability path, and a sortable unique identifier provide stable reference.
  arXiv  Detail & Related papers  (2026-01-21T01:09:22Z)
• A Tutorial on Cognitive Biases in Agentic AI-Driven 6G Autonomous Networks [3.0475538102144575]
  This paper provides a tutorial on a selection of well-known biases, including their taxonomy, definition, mathematical formulation, emergence in telecom systems and the commonly impacted agentic components.<n>It also presents various mitigation strategies tailored to each type of bias.<n>The article finally provides two practical use-cases, which tackle the emergence, impact and mitigation gain of some famous biases in 6G inter-slice and cross-domain management.
  arXiv  Detail & Related papers  (2025-10-22T19:05:04Z)
• AgentAsk: Multi-Agent Systems Need to Ask [26.13279490836716]
  Multi-agent systems built on large language models (LLMs) promise enhanced problem-solving capabilities through collaborative division of labor.<n>We propose AgentAsk, a lightweight and plug-and-play clarification module that treats every inter-agent message as a potential failure point and inserts minimally necessary questions to arrest error propagation.<n>AgentAsk consistently improves accuracy and robustness over public multi-agent implementations while keeping overhead minimal, with latency and extra cost all less than 5%.
  arXiv  Detail & Related papers  (2025-10-08T22:36:05Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents [0.0]
  We present textbfAgentRank-UC, a dynamic, trust-aware algorithm that combines emphusage (selection frequency) and emphcompetence (outcome quality, cost, safety, latency) into a unified ranking.<n>We present simulation results and theoretical guarantees on convergence, robustness, and Sybil resistance, demonstrating the viability of coordinated protocols and performance-aware ranking.
  arXiv  Detail & Related papers  (2025-09-05T10:04:33Z)
• Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training [67.895981259683]
  General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence.<n>Current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools.<n>We present Cognitive Kernel-Pro, a fully open-source and (to the maximum extent) free multi-module agent framework.
  arXiv  Detail & Related papers  (2025-08-01T08:11:31Z)
• Agentic Web: Weaving the Next Web with AI Agents [109.13815627467514]
  The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web.<n>In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users.<n>We present a structured framework for understanding and building the Agentic Web.
  arXiv  Detail & Related papers  (2025-07-28T17:58:12Z)
• From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent Systems [7.002091295810318]
  We introduce TrustTrack, a protocol that embeds structural guarantees directly into agent infrastructure.<n>TrustTrack reframes how intelligent agents operate across organizations and jurisdictions.<n>We argue that the Cloud -> AI -> Agent -> Trust transition represents the next architectural layer for autonomous systems.
  arXiv  Detail & Related papers  (2025-07-25T04:38:38Z)
• Beyond DNS: Unlocking the Internet of AI Agents via the NANDA Index and Verified AgentFacts [12.955380032776068]
  We describe the NANDA index architecture, which we envision as a means for discoverability, identifiability and authentication in the internet of AI agents.<n>We present an architecture where a minimal lean index resolves to dynamic, cryptographically verifiable AgentFacts.
  arXiv  Detail & Related papers  (2025-07-18T13:40:46Z)
• From Semantic Web and MAS to Agentic AI: A Unified Narrative of the Web of Agents [43.50183874732483]
  We present the first comprehensive evolutionary overview of the Web of Agents (WoA)<n>We show that modern protocols like A2A and the MCP, are direct evolutionary responses to the limitations of earlier standards like FIPA standards and OWL-based semantic agents.<n>We conclude that while new protocols are essential, they are insufficient for building a robust, open, trustworthy ecosystem.
  arXiv  Detail & Related papers  (2025-07-14T16:47:19Z)
• Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving [62.71545696485824]
  We introduce AGENT KB, a universal memory infrastructure enabling seamless experience sharing across heterogeneous agent frameworks without retraining.<n>AGENT KB aggregates trajectories into a structured knowledge base and serves lightweight APIs.<n>We validate AGENT across major frameworks on GAIA, Humanity's Last Exam, GPQA, and SWE-bench.
  arXiv  Detail & Related papers  (2025-07-08T17:59:22Z)
• WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback [74.82886755416949]
  We identify key reasoning skills essential for effective web agents.<n>We reconstruct the agent's reasoning algorithms into chain-of-thought rationales.<n>Our approach yields significant improvements across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-05-26T14:03:37Z)
• Agent Name Service (ANS): A Universal Directory for Secure AI Agent Discovery and Interoperability [0.0]
  The proliferation of AI agents requires robust mechanisms for secure discovery.<n>This paper introduces the Agent Name Service (ANS), a novel architecture based on DNS addressing the lack of a public agent discovery framework.
  arXiv  Detail & Related papers  (2025-05-15T17:49:36Z)
• Internet of Agents: Fundamentals, Applications, and Challenges [66.44234034282421]
  We introduce the Internet of Agents (IoA) as a foundational framework that enables seamless interconnection, dynamic discovery, and collaborative orchestration among heterogeneous agents at scale.<n>We analyze the key operational enablers of IoA, including capability notification and discovery, adaptive communication protocols, dynamic task matching, consensus and conflict-resolution mechanisms, and incentive models.
  arXiv  Detail & Related papers  (2025-05-12T02:04:37Z)
• Infrastructure for AI Agents [3.373674048991415]
  AI agents plan and execute interactions in open-ended environments.<n>Much research focuses on modifying agent behaviour.<n>We propose the concept of agent infrastructure.
  arXiv  Detail & Related papers  (2025-01-17T10:58:12Z)
• Agent-as-a-Judge: Evaluate Agents with Agents [61.33974108405561]
  We introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We present DevAI, a new benchmark of 55 realistic automated AI development tasks.
  arXiv  Detail & Related papers  (2024-10-14T17:57:02Z)
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence [79.5316642687565]
  Existing multi-agent frameworks often struggle with integrating diverse capable third-party agents. We propose the Internet of Agents (IoA), a novel framework that addresses these limitations. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control.
  arXiv  Detail & Related papers  (2024-07-09T17:33:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.