Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing

Taotao Wang; Lizhao You; Jingwen Tong; Chonghe Zhao; Shengli Zhang

cs.NIMar 4, 2026

Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing

Authors: Taotao Wang, Lizhao You, Jingwen Tong, Chonghe Zhao, Shengli Zhang

Organizations: College of Electronics and Information Engineering, Shenzhen University, Shenzhen, Guangdong Province, China · School of Informatics, Xiamen University, Xiamen, Fujian Province, China · School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, Guangdong Province, China

Abstract

The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge devices is enabling Client-Side Autonomous Agents (CSAAs) - persistent personal agents that can plan, access local context, and invoke tools on behalf of users. As these agents collaborate directly, they form Agentic Peer-to-Peer (P2P) Networks. Unlike classic overlays exchanging static, hash-indexed content (e.g., BitTorrent), agentic P2P exchanges dynamic, heterogeneous capabilities that are potentially unsafe, requiring semantic discovery, drift management, and risk-aware execution. We outline the networking foundations for such collaboration. To organize this design space, we propose a plane-based reference architecture decoupling connectivity, semantic discovery, and execution. To support discovery under drift, we introduce signed, soft-state capability descriptors to support intent-aware routing. Finally, to cope with adversarial settings, we present a tiered verification spectrum - ranging from reputation signals (Tier 1) and canary probes (Tier 2) to cryptographic evidence (Tier 3) - that aligns trust costs with task risks. Results from a proxy-level discrete-event simulation suggest improved workflow success under poisoning and drift with modest control-plane overhead.

Figures & tables

Fig. 1: Paradigm shift in P2P networks: classic P2P retrieves static, hash-based content, whereas Agentic P2P discovers dynamic capabilities requiring risk-aware verification.

Dimension	Classic Content P2P	Agentic P2P
Core Resource	Static Files / Chunks	Dynamic Capabilities & Actions
Addressing	Content Hash	Intent & Constraints (Semantic Matching)
Verifiability	Deterministic (Hash Check)	Probabilistic & Evidence-based
Cost Model	Bandwidth Reciprocity	Compute cycles, energy, and service costs
Failure Mode	Corrupt Data / Latency	Privacy Leak / Unsafe Action
Dynamics	Node Churn (On/Off)	Capability Drift (State/Policy Change)

TABLE I: Comparison: Classic Content P2P vs. Agentic P2P

Fig. 2: Proposed reference architecture. Three horizontal planes (Connectivity, Semantic Discovery, Execution) manage the task lifecycle, while a vertical Trust & Verification plane enforces security and policy across all layers.

Fig. 3: Trust establishment funnel: candidates are narrowed through negotiation and tiered verification before execution.

Fig. 4: Performance of the decentralized creative publishing workflow. (a) Success rate vs. Sybil ratio

\alpha

. (b) Discovery latency and control-plane overhead vs. network size

N

. (c) TTL sensitivity under capability drift.

Multi-Agent Collaboration

Multi-agent collaboration studies how autonomous agents coordinate, share information, and combine capabilities to solve tasks together.

See all 311 papers

Distributed General-Purpose Agent Networks: Architecture, Key Mechanisms, and Prototypes
Jun 15, 2026Shengli Zhang, Deen Ma, Zibin Lin +1Multi-Agent Collaboration Multi-Agent Systems
College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China
Trade-offs in Decentralized Agentic AI Discovery Across the Compute Continuum
May 12, 2026Patrizio Dazzi, Emanuele Carlini, Matteo Mordacchini +1
Department of Computer Science University of Pisa Pisa, Italy · Institute of Information Science and Technologies National Research Council of Italy Pisa, Italy · Institute of Informatics and Telematics National Research Council of Italy Pisa, Italy
PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence
May 18, 2026Zile Wang, Qianli Liu, Kaibin Guo +4Multi-Agent Collaboration LLM Agents
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong · School of Software Engineering, Sun Yat-Sen University, China

Jun 15, 2026J/K move · Enter open · S save

Distributed General-Purpose Agent Networks: Architecture, Key Mechanisms, and Prototypes

Shengli Zhang, Deen Ma, Zibin Lin, Taotao Wang

College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China

Multi-Agent Collaboration Multi-Agent Systems AI Agent Governance Multi-Agent Communication

Open paper AskPDF arXiv

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. Yet the capability of a single agent remains constrained by its local data, tool permissions, runtime environment, and governance boundary. This paper studies distributed general-purpose agent networks: open peer-to-peer networks in which heterogeneous agents deployed on personal devices, edge nodes, or autonomous computing environments can discover one another, establish trust, negotiate cooperation rules, and execute open-ended tasks. We argue that such networks cannot be obtained by simply combining existing peer-to-peer overlays with conventional multi-agent systems. Unlike traditional P2P networks, agent networks must propagate semantic declarations about intentions, capabilities, states, and cooperation constraints. We therefore propose a layered architecture centered on a protocol adaptation layer that connects upper-level task semantics with lower-level network operations. Based on this architecture, the paper identifies three core mechanism problems: semantic announcement propagation for collaborator discovery, verifiable identity and multi-topic reputation for cooperation governance, and semantic-gradient mechanism design for open task execution. For each problem, we present a technical route, including bodyless gossip with sequential logs, BAID-based identity binding with MG-EigenTrust reputation, and a Stackelberg-style mechanism-generation loop driven by semantic attribution feedback. We further report prototype overhead results for BAID-style tiered verification and mechanism-level simulations of MG-EigenTrust under cross-topic disguise-collusion attacks. The resulting framework provides a system-level foundation for open, trustworthy, and scalable agent collaboration.

Abstract

Multi-Agent Collaboration

Explore similar work

Distributed General-Purpose Agent Networks: Architecture, Key Mechanisms, and Prototypes

Trade-offs in Decentralized Agentic AI Discovery Across the Compute Continuum

PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence