SOURCE-LINKED INTELLIGENCE

State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, session history, live inventory), and a distinct failure class we call direction drift: task-complete responses whose chosen direction misaligns with the current state. SGC externalises state-dependent control into rule kernels over structured inputs and three primary state slices, via Perception, Grounding, and Interaction wrappers with explicit conditioning dependencies. We evaluate SGC on a 200-session anonymised benchmark ($\approx$1,000 assistan

Read original source ↗ Open in workspace

recordType

paper

region

Global