Models model language model announce platform analysis report

Human-in-the-Loop Control of Objective Drift in LLM-Assisted Computer Science Education

ArXiv CS.AIby Mark Dranias, Adam WhitleyApril 2, 20261 min read0 views

arXiv:2604.00281v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge from stated task specifications. Existing instructional responses frequently emphasize tool-specific prompting practices, limiting durability as AI platforms evolve. This paper adopts a human-centered stance, treating human-in-the-loop (HITL) control as a stable educational problem rather than a transitional step toward AI autonomy. Drawing on systems engineering and control-theoretic concepts, we frame objectives and world models as operational artifacts that students configure to stabilize AI-assisted work. We propose a pilot u

View PDF

Abstract:Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge from stated task specifications. Existing instructional responses frequently emphasize tool-specific prompting practices, limiting durability as AI platforms evolve. This paper adopts a human-centered stance, treating human-in-the-loop (HITL) control as a stable educational problem rather than a transitional step toward AI autonomy. Drawing on systems engineering and control-theoretic concepts, we frame objectives and world models as operational artifacts that students configure to stabilize AI-assisted work. We propose a pilot undergraduate CS laboratory curriculum that explicitly separates planning from execution and trains students to specify acceptance criteria and architectural constraints prior to code generation. In selected labs, the curriculum also introduces deliberate, concept-aligned drift to support diagnosis and recovery from specification violations. We report a sensitivity power analysis for a three-arm pilot design comparing unstructured AI use, structured planning, and structured planning with injected drift, establishing detectable effect sizes under realistic section-level constraints. The contribution is a theory-driven, methodologically explicit foundation for HITL pedagogy that renders control competencies teachable across evolving AI tools.

Comments: 8 pages

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2604.00281 [cs.AI]

(or arXiv:2604.00281v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2604.00281

arXiv-issued DOI via DataCite (pending registration)