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

arXiv:2603.03753v2 Announce Type: replace-cross 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.

Related

• Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models
• Collaborative Edge-to-Server Inference for Vision-Language Models
• MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents
• CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization
• Can Open-Source LLM Agents Replace Static Application Security Testing Tools? An Empirical Assessment

Source: arXiv cs.AI | 2026-10-12