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

arXiv: https://arxiv.org/abs/2604.00281 · HTML: https://mlsanity.com/paper/2604.00281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?](https://mlsanity.com/paper/2411.02093/) (2024)
- [Prompting Science Report 2: The Decreasing Value of Chain of Thought in Prompting](https://mlsanity.com/paper/2506.07142/) (2025)
- [Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models](https://mlsanity.com/paper/2505.24187/) (2025)
- [Prompting Science Report 1: Prompt Engineering is Complicated and Contingent](https://mlsanity.com/paper/2503.04818/) (2025)
- [A Survey of LLM-Based Applications in Programming Education: Balancing Automation and Human Oversight](https://mlsanity.com/paper/2510.03719/) (2025)

## Abstract (arXiv)

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.