AI RESEARCH
PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agents
arXiv CS.AI
•
ArXi:2603.18377v1 Announce Type: cross Cloud-hosted large language models (LLMs) have become the de facto planners in agentic systems, coordinating tools and guiding execution over local environments. In many deployments, however, the environment being planned over is private, containing source code, files, credentials, and metadata that cannot be exposed to the cloud.