PerAgents focuses on the critical systems-level challenges of transitioning from narrow, single-task edge AI to general-purpose, autonomous AI agents operating in physical environments. Currently, foundation models are trapped in the cloud due to massive computational requirements. This workshop explores how large-scale models such as Large Language Models (LLMs), Vision-Language Models (VLMs), and Multimodal Language Models (MLMs) can be compressed, decentralized, and securely integrated with pervasive sensor networks.
A defining feature of pervasive agentic systems is their domain-agnostic architectures. The exact same edge-computing architecture, split learning pipeline, and VLM integration used to fuse IoT telemetry and satellite data for a real-time decision-support system in precision agriculture can be deployed in a clinical setting to fuse wearable sensor streams for continuous patient monitoring. PerAgents investigates the underlying system architecture that remains constant even as the environmental context changes.
A focused, high-visibility workshop for researchers building the systems that make pervasive agentic intelligence practical, secure, and deployable.
Position your work in front of a community that cares about real deployment, edge constraints, and end-to-end architecture.
PerAgents connects AI, edge systems, and applied domains such as health, agriculture, smart cities, and industrial automation.
The format prioritizes feedback, debate, and practical next steps rather than dense, one-way presentations.
PerAgents follows the official PerCom 2027 submission workflow and IEEE formatting rules.
Use the official IEEE LaTeX or Microsoft Word conference templates and follow the two-column formatting instructions.
Open IEEE TemplatesSubmit your paper through the official PerCom 2027 system for the main conference and associated events.
Go to PerCom HotCRP
