Search papers, labs, and topics across Lattice.
This paper introduces the concept of "intent compilation" to address the challenges of deploying AI agents in open-world environments, where verification is distributed across multiple dimensions. It formalizes the "closure gap" as a vector representing residual openness and defines "delegation envelopes" as pre-authorized action spaces. The authors propose that interventions to close these gaps can outperform additional inference-time search, offering a new approach to ensuring reliable agent behavior.
Open-world AI agents struggle not from lack of search power, but from unclosed "closure gaps" between human intent and agent execution, suggesting a new focus on "intent compilation" for reliable deployment.
Recent work has framed intelligence in verifiable tasks as reducing time-to-solution through learned structure and test-time search, while systems work has explored learned runtimes in which computation, memory and I/O migrate into model state. These perspectives do not explain why capable models remain difficult to deploy in open institutions. We propose intent compilation: the transformation of partially specified human purpose into inspectable artifacts that bind execution. The relevant deployment distinction is closed-world solver versus open-world agent. In closed worlds, a checker is largely given; in open worlds, verification is distributed across semantic, evidentiary, procedural and institutional dimensions. Weformalize this residual openness as a closure-gap vector, define delegation envelopes as pre-authorized regions of action space, distinguish misclosure from undersearch, and outline benchmark metrics for testing when closure interventions outperform additional inference-time search.
