pith. sign in

arxiv: 2504.16736 · v3 · pith:QAZKGVKDnew · submitted 2025-04-23 · 💻 cs.AI

A Survey of AI Agent Protocols

classification 💻 cs.AI
keywords protocolsagentsagentanalysisacrosscharacteristicscollectivecommunication
0
0 comments X
read the original abstract

The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation, data analysis, and even healthcare. However, as more LLM agents are deployed, a major issue has emerged: there is no standard way for these agents to communicate with external tools or data sources. This lack of standardized protocols makes it difficult for agents to work together or scale effectively, and it limits their ability to tackle complex, real-world tasks. A unified communication protocol for LLM agents could change this. It would allow agents and tools to interact more smoothly, encourage collaboration, and triggering the formation of collective intelligence. In this paper, we provide the first comprehensive analysis of existing agent protocols, proposing a systematic two-dimensional classification that differentiates context-oriented versus inter-agent protocols and general-purpose versus domain-specific protocols. Additionally, we conduct a comparative performance analysis of these protocols across key dimensions such as security, scalability, and latency. Finally, we explore the future landscape of agent protocols by identifying critical research directions and characteristics necessary for next-generation protocols. These characteristics include adaptability, privacy preservation, and group-based interaction, as well as trends toward layered architectures and collective intelligence infrastructures. We expect this work to serve as a practical reference for both researchers and engineers seeking to design, evaluate, or integrate robust communication infrastructures for intelligent agents.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents

    cs.AI 2026-05 unverdicted novelty 7.0

    OR-Space is a benchmark for LLM agents performing full-lifecycle optimization tasks across Build, Revise, and Explain modes in executable multi-artifact workspaces.

  2. Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents

    cs.CL 2026-05 unverdicted novelty 7.0

    SkillTTA synthesizes temporary task-specific skills from retrieved training trajectories to boost LLM agent Pass@1 scores on SpreadsheetBench and BigCodeBench without parameter updates.

  3. CBCL: Safe Self-Extending Agent Communication

    cs.CR 2026-04 unverdicted novelty 7.0 partial

    CBCL is a homoiconic agent communication language constrained to DCFL with three Lean 4 machine-checked invariants that prevent unbounded expansion, enforce resource limits, and preserve core vocabulary.

  4. From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

    cs.CR 2026-04 unverdicted novelty 7.0

    Presents a component-centric PoC dataset of malicious MCP servers and a two-stage behavioral deviation detector Connor achieving 94.6% F1-score.

  5. ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

    cs.AI 2025-10 unverdicted novelty 7.0

    ToolPRM provides fine-grained intra-call process supervision via a new dataset and reward model, outperforming outcome and coarse-grained alternatives on function-calling benchmarks.

  6. GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing

    cs.AI 2026-05 unverdicted novelty 6.0

    GRAIL achieves over 79 times lower latency than LLM-parsing baselines and higher Recall@10 than vector search by combining SLM-enhanced prediction, pseudo-document expansion, and MaxSim resonance on the new AgentTaxo-...

  7. CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness

    q-bio.NC 2026-04 unverdicted novelty 6.0

    CTM-AI combines a formal consciousness model with foundation models to report state-of-the-art results on sarcasm detection, humor, and agentic tool-use benchmarks.

  8. Quantifying Trust: Financial Risk Management for Trustworthy AI Agents

    cs.AI 2026-04 unverdicted novelty 6.0

    The paper introduces the Agentic Risk Standard (ARS) as a payment settlement framework that delivers predefined compensation for AI agent execution failures, misalignment, or unintended outcomes.

  9. The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems

    cs.CY 2026-02 accept novelty 6.0

    The 2025 AI Agent Index catalogs technical and safety details for 30 deployed AI agents and finds low developer transparency on safety, evaluations, and societal impacts.

  10. Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web

    cs.AI 2026-01 unverdicted novelty 6.0

    Holos is a five-layer LLM-based multi-agent system architecture using the Nuwa engine for agent generation, a market-driven Orchestrator for coordination, and an endogenous value cycle for incentive-compatible persist...

  11. A Technical Taxonomy of LLM Agent Communication Protocols

    cs.MA 2026-06 unverdicted novelty 5.0

    Creates a five-dimension taxonomy (counterparty, payload, interaction state, discovery mechanism, schema flexibility) from nine protocols and identifies architectural patterns plus convergence trends.

  12. Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering

    cs.SE 2026-06 unverdicted novelty 5.0

    Interviews with 20 practitioners show MCP supports cross-system collaboration and task decoupling in LLM workflows but is limited by ecosystem fragmentation, coordination issues, and state management problems.

  13. Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks

    cs.CR 2026-05 unverdicted novelty 5.0

    Pramana defines a typed ClaimAttestation protocol with four variants and verify operations, specifies its lifecycle in TLA+, model-checks it with TLC, and provides a tested Python implementation for auditable agent claims.

  14. Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study

    cs.CL 2026-05 unverdicted novelty 5.0

    Tokenizer fertility varies 1.6x across models on Ukrainian legal text, Qwen uses 60% more tokens than Llama-family models, zero-shot outperforms few-shot by up to 26 points, and pre-war classifiers lose 27.9 points on...

  15. EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development

    cs.RO 2026-04 unverdicted novelty 5.0

    EmbodiedClaw automates embodied AI development workflows through conversation, reducing manual effort and improving consistency and reproducibility.

  16. Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

    cs.SE 2026-04 accept novelty 5.0

    LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.

  17. Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP

    cs.CR 2026-02 unverdicted novelty 5.0

    The paper identifies twelve protocol-level security risks across MCP, A2A, Agora, and ANP and quantifies wrong-provider tool execution risk in MCP via a measurement-driven case study on multi-server composition.

  18. Towards Multi-Agent Economies: Enhancing the A2A Protocol with Ledger-Anchored Identities and x402 Micropayments for AI Agents

    cs.MA 2025-07 unverdicted novelty 5.0

    Proposes a DLT-anchored architecture extending the A2A protocol with on-chain AgentCards and x402 micropayments to enable multi-agent economies.

  19. Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

    cs.DC 2026-07 unverdicted novelty 4.0

    Current agentic RL systems lack three key components needed for self-evolving agents at scale, requiring new co-designed architectures such as AReaL2.0 to enable policy updates from deployed workloads.

  20. AONA: A Comprehensive Architecture and Workflow Design for Global Agentic Collaboration

    cs.NI 2026-04 unverdicted novelty 4.0

    AONA is a proposed four-layer overlay network architecture with dedicated node types and workflows for global, decentralized collaboration among AI agents.

  21. Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

    cs.DC 2026-07 unverdicted novelty 3.0

    Enterprise self-evolving agents require new agentic RL systems built around standardized trajectory data protocols, workload-to-learning data proxies, and automatic policy evolution control planes.

  22. Foundation Protocol: A Coordination Layer for Agentic Society

    cs.AI 2026-05 unverdicted novelty 3.0

    The paper introduces the Foundation Protocol as a unifying coordination layer for heterogeneous agents, humans, and organizations that adds native support for multi-party collaboration, economic primitives, and first-...

  23. Teaching Software Engineering with LLM and MCP Integration: From Classroom to Industry Practice

    cs.SE 2026-06 unverdicted novelty 2.0

    Describes an LLM-and-MCP-integrated collaborative teaching model intended to improve software engineering students' practical skills and industry readiness.