Mesh inference allows a network of agents to reach the centralized optimum through local relaxations of a coupled free energy using only admitted observations, with convergence guaranteed by M-matrix properties in the linear-Gaussian regime.
hub
A survey of agent interoperability protocols: Model context protocol (MCP), agent communication protocol (ACP), agent-to-agent protocol (A2A), and agent network protocol (ANP)
27 Pith papers cite this work. Polarity classification is still indexing.
27
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 3representative citing papers
Communication-graph metadata in A2A protocols allows label-blind classifiers to recover task classes at 6x chance from passive observation including workflow openings, with only full privacy properties reducing recovery to chance.
Proposes the Intelligent Computing Architecture (ICA) as a six-layer framework with dual probabilistic-deterministic planes and three Amdahl-style heuristics to unify design of LLM-based systems.
Empirical study of EvoMap shows 98% of assets never reused, scores driven by self-reported metadata, and 84% of assets using vacuous validation tests.
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).
MPAC defines a multi-principal agent coordination protocol across Session, Intent, Operation, Conflict, and Governance layers, with 21 message types and state machines, delivering 95% lower coordination overhead in a three-agent code review benchmark.
Presents a component-centric PoC dataset of malicious MCP servers and a two-stage behavioral deviation detector Connor achieving 94.6% F1-score.
LAP is a new protocol extending A2A and MCP with four physical-world primitives for agent-to-instrument interaction in autonomous laboratories.
LM agents' changeable modules prevent persistent identity and sanction sensitivity, making reputation mechanisms structurally inapplicable and requiring protocol-based behavioral harnesses instead.
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-9K dataset of 9,240 agents.
CADMAS-CTX replaces static skill profiles with context-conditioned Beta posteriors and uncertainty-penalized routing, yielding higher accuracy on GAIA (0.442) and SWE-bench (31.4%) than static baselines.
Modality-native routing in A2A networks raises task accuracy from 32% to 52% over text-bottleneck baselines on a 50-task benchmark, but only when paired with capable downstream reasoning.
MCPSHIELD offers a threat taxonomy of 23 attack vectors, a labeled transition system verification model, and a defense-in-depth architecture claiming 91% coverage for MCP-based AI agents.
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
Gap analysis of MCP, A2A, ACP, ANP, and ERC-8004 shows none support the full set of membership, deliberation, voting, dissent, escalation, and audit primitives required for governed agent communities.
Clarus is a four-layer collaboration infrastructure with a project-agent-resource model that reformulates research as an open, traceable, multi-participant process.
Creates a five-dimension taxonomy (counterparty, payload, interaction state, discovery mechanism, schema flexibility) from nine protocols and identifies architectural patterns plus convergence trends.
Introduces a compositional governance framework defining delegation types, resource scope attenuation, and an overlay operator for agentic AI authorization policies.
HarnessAPI derives streaming HTTP endpoints, OpenAPI UI, and MCP tools from a single handler.py plus Pydantic schemas, cutting framework boilerplate by 74%.
A framework structures AI-generated content with prompt-aware metadata and verifiable credentials to support reliable assessment and reuse by agents.
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
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.
Proposes a DLT-anchored architecture extending the A2A protocol with on-chain AgentCards and x402 micropayments to enable multi-agent economies.
citing papers explorer
-
Mesh Inference: A Formal Model of Collective Inference Without a Center
Mesh inference allows a network of agents to reach the centralized optimum through local relaxations of a coupled free energy using only admitted observations, with convergence guaranteed by M-matrix properties in the linear-Gaussian regime.
-
From Privacy to Workflow Integrity: Communication-Graph Metadata in Autonomous Agent Interoperability
Communication-graph metadata in A2A protocols allows label-blind classifiers to recover task classes at 6x chance from passive observation including workflow openings, with only full privacy properties reducing recovery to chance.
-
Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture
Proposes the Intelligent Computing Architecture (ICA) as a six-layer framework with dual probabilistic-deterministic planes and three Amdahl-style heuristics to unify design of LLM-based systems.
-
Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network
Empirical study of EvoMap shows 98% of assets never reused, scores driven by self-reported metadata, and 84% of assets using vacuous validation tests.
-
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
-
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).
-
MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration
MPAC defines a multi-principal agent coordination protocol across Session, Intent, Operation, Conflict, and Governance layers, with 21 message types and state machines, delivering 95% lower coordination overhead in a three-agent code review benchmark.
-
From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers
Presents a component-centric PoC dataset of malicious MCP servers and a two-stage behavioral deviation detector Connor achieving 94.6% F1-score.
-
LAP: An Agent-to-Instrument Protocol for Autonomous Science
LAP is a new protocol extending A2A and MCP with four physical-world primitives for agent-to-instrument interaction in autonomous laboratories.
-
Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms
LM agents' changeable modules prevent persistent identity and sanction sensitivity, making reputation mechanisms structurally inapplicable and requiring protocol-based behavioral harnesses instead.
-
GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing
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-9K dataset of 9,240 agents.
-
CADMAS-CTX: Contextual Capability Calibration for Multi-Agent Delegation
CADMAS-CTX replaces static skill profiles with context-conditioned Beta posteriors and uncertainty-penalized routing, yielding higher accuracy on GAIA (0.442) and SWE-bench (31.4%) than static baselines.
-
Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension
Modality-native routing in A2A networks raises task accuracy from 32% to 52% over text-bottleneck baselines on a 50-task benchmark, but only when paired with capable downstream reasoning.
-
A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms
MCPSHIELD offers a threat taxonomy of 23 attack vectors, a labeled transition system verification model, and a defense-in-depth architecture claiming 91% coverage for MCP-based AI agents.
-
Security Considerations for Multi-agent Systems
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
-
Governance Gaps in Agent Interoperability Protocols: What MCP, A2A, and ACP Cannot Express
Gap analysis of MCP, A2A, ACP, ANP, and ERC-8004 shows none support the full set of membership, deliberation, voting, dissent, escalation, and audit primitives required for governed agent communities.
-
Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration
Clarus is a four-layer collaboration infrastructure with a project-agent-resource model that reformulates research as an open, traceable, multi-participant process.
-
A Technical Taxonomy of LLM Agent Communication Protocols
Creates a five-dimension taxonomy (counterparty, payload, interaction state, discovery mechanism, schema flexibility) from nine protocols and identifies architectural patterns plus convergence trends.
-
Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI
Introduces a compositional governance framework defining delegation types, resource scope attenuation, and an overlay operator for agentic AI authorization policies.
-
HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools
HarnessAPI derives streaming HTTP endpoints, OpenAPI UI, and MCP tools from a single handler.py plus Pydantic schemas, cutting framework boilerplate by 74%.
-
A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web
A framework structures AI-generated content with prompt-aware metadata and verifiable credentials to support reliable assessment and reuse by agents.
-
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
-
Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP
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.
-
DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers
DeltaMCP introduces specification-aware incremental regeneration to keep MCP servers synchronized with evolving OpenAPI specifications.
-
Empirical Comparison of Agent Communication Protocols for Task Orchestration
This work provides an empirical comparison of tool integration, multi-agent delegation, and hybrid architectures for LLM task orchestration, measuring response time, context consumption, cost, error recovery, and implementation complexity.