paper-with-me

홈 › Papers

Inter-Agent Trust Models: A Comparative Study of Brief, Claim, Proof, Stake, Reputation and Constraint in Agentic Web Protocol Design-A2A, AP2, ERC-8004, and Beyond

2025-11-05 · Botao 'Amber' Hu, Helena Rong arxiv

As the "agentic web" takes shape-billions of AI agents (often LLM-powered) autonomously transacting and collaborating-trust shifts from human oversight to protocol design. In 2025, several inter-agent protocols crystallized this shift, including Google's Agent-to-Agent (A2A), Agent Payments Protocol (AP2), and Ethereum's ERC-8004 "Trustless Agents," yet their underlying trust assumptions remain under-examined. This paper presents a comparative study of trust models in inter-agent protocol design: Brief (self- or third-party verifiable claims), Claim (self-proclaimed capabilities and identity, e.g. AgentCard), Proof (cryptographic verification, including zero-knowledge proofs and trusted execution environment attestations), Stake (bonded collateral with slashing and insurance), Reputation (crowd feedback and graph-based trust signals), and Constraint (sandboxing and capability bounding). For each, we analyze assumptions, attack surfaces, and design trade-offs, with particular emphasis on LLM-specific fragilities-prompt injection, sycophancy/nudge-susceptibility, hallucination, deception, and misalignment-that render purely reputational or claim-only approaches brittle. Our findings indicate no single mechanism suffices. We argue for trustless-by-default architectures anchored in Proof and Stake to gate high-impact actions, augmented by Brief for identity and discovery and Reputation overlays for flexibility and social signals. We comparatively evaluate A2A, AP2, ERC-8004 and related historical variations in academic research under metrics spanning security, privacy, latency/cost, and social robustness (Sybil/collusion/whitewashing resistance). We conclude with hybrid trust model recommendations that mitigate reputation gaming and misinformed LLM behavior, and we distill actionable design guidelines for safer, interoperable, and scalable agent economies.

📄 PDF Abstract BibTeX arXiv:2511.03434

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Trust-MARL: Trust-Based Multi-Agent Reinforcement Learning Framework for Cooperative On-Ramp Merging Control in Heterogeneous Traffic Flow

2025-06-14 · Jie Pan, Tianyi Wang, Christian Claudel, Jing Shi

Intelligent transportation systems require connected and automated vehicles (CAVs) to conduct safe and efficient cooperation with human-driven vehicles (HVs) in complex real-world traffic environments. However, the inher…

Multi-agent Reinforcement Learning

On the Importance of Trust in Next-Generation Networked CPS Systems: An AI Perspective

2021-04-16 · Anousheh Gholami, Nariman Torkzaban, John S. Baras

With the increasing scale, complexity, and heterogeneity of the next generation networked systems, seamless control, management, and security of such systems becomes increasingly challenging. Many diverse applications ha…

Decision MakingFederated LearningManagement

From Prompt to Product: A Human-Centered Benchmark of Agentic App Generation Systems

2025-12-19 · Marcos Ortiz, Justin Hill, Collin Overbay, Ingrida Semenec 외 arxiv

Agentic AI systems capable of generating full-stack web applications from natural language prompts ("prompt- to-app") represent a significant shift in software development. However, evaluating these systems remains chall…

Can We Trust AI Agents? A Case Study of an LLM-Based Multi-Agent System for Ethical AI

2024-10-25 · José Antonio Siqueira de Cerqueira, Mamia Agbese, Rebekah Rousi, Nannan Xi 외

AI-based systems, including Large Language Models (LLM), impact millions by supporting diverse tasks but face issues like misinformation, bias, and misuse. AI ethics is crucial as new technologies and concerns emerge, bu…

Bias DetectionEthicsFairnessMisinformation

Trusting Your AI Agent Emotionally and Cognitively: Development and Validation of a Semantic Differential Scale for AI Trust

2024-07-25 · Ruoxi Shang, Gary Hsieh, Chirag Shah

Trust is not just a cognitive issue but also an emotional one, yet the research in human-AI interactions has primarily focused on the cognitive route of trust development. Recent work has highlighted the importance of st…

AI Agent