AI RESEARCH

Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction

arXiv CS.AI

ArXi:2605.23928v1 Announce Type: new We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed agents that advance shared tasks without waiting for user prompts. The architecture rests on three mutually reinforcing mechanisms. Write-time context assembly precomputes enriched typed attributes via Groker agents, assembling interaction context as a deterministic pure function of graph state; context blocks are byte-identical across turns between semantic changes, enabling near-100% KV-cache reuse.