Large Language Models (LLMs) challenge conventional automated programming assessment because students can now produce functionally correct code without demonstrating corresponding understanding. This paper makes two contributions. First, it reports a saturation-based scoping review of conversational assessment approaches in programming education. The review identifies three dominant architectural families: rule-based or template-driven systems, LLM-based systems, and hybrid systems. Across the literature, conversational agents appear promising for scalable feedback and deeper probing of code understanding, but important limitations remain around hallucinations, over-reliance, privacy, integrity, and deployment constraints. Second, the paper synthesizes these findings into a Hybrid Socratic Framework for integrating conversational verification into Automated Programming Assessment Systems (APASs). The framework combines deterministic code analysis with a dual-agent conversational layer, knowledge tracking, scaffolded questioning, and guardrails that tie prompts to runtime facts. The paper also discusses practical safeguards against LLM-generated explanations, including proctored deployment modes, randomized trace questions, stepwise reasoning tied to concrete execution states, and local-model deployment options for privacy-sensitive settings. Rather than replacing conventional testing, the framework is intended as a complementary layer for verifying whether students understand the code they submit.
Figures & tables
Figure 1: Keyword groups and query template used to derive the five search string variants.
Figure 2: PRISMA-style flow diagram of identification, screening, eligibility, and inclusion.
Figure 3: Hybrid Socratic Framework for chatbot-based assessment in APASs.
Figure 4: Proof of concept, Tier 1: scenario-based multiple-choice question generated by the Instructor Agent.
Figure 5: Proof of concept, Tier 2: open-ended explanation graded by the Verifier Agent.
Worked examples are step-by-step solutions to problems in a specific domain, offered to students to acquire domain-specific problem-solving skills. The effectiveness of worked examples could be enhanced by combining them with self-explanations, which ask students to explain rather than passively study each problem-solving step. The main challenge of this approach is assessing the correctness of the student's explanations. In the prevailing approach, student explanations are judged by their semantic similarity to an instructor's or domain expert's explanation. Given recent advances in LLM-based automated scoring, it remains unclear whether semantic similarity methods are still the most effective technique to automatically score textual student responses like essays or code explanations. Comparing these methods also requires quality datasets that offer distinctive features such as balanced class distributions and domain-specific labeled data for automated scoring tasks. In this paper, we present a rigorous comparison between LLMs and semantic similarity used for automated scoring, framed as a binary classification task.
Arun-Balajiee Lekshmi-Narayanan, Mohammad Hassany, Peter Brusilovsky
The rapid emergence of Large Language Models (LLMs) presents both opportunities and challenges for programming education. While students increasingly use generative AI tools, direct access often hinders the learning process by providing complete solutions rather than pedagogical hints. Concurrently, educators face significant workload and scalability challenges when providing timely, personalized feedback. This study investigates the capabilities of LLMs to safely and effectively assist educators in answering student questions within a CS1 programming course. To achieve this, we established a rigorous, reproducible evaluation process by curating a benchmark dataset of 170 authentic student questions from a learning management system, paired with ground-truth responses authored by subject matter experts. Because traditional text-matching metrics are insufficient for evaluating open-ended educational responses, we developed and validated a custom LLM-as-a-Judge metric optimized for assessing pedagogical accuracy. Our findings demonstrate that models, such as Gemini 3 flash, can surpass the quality baseline of typical educator responses, achieving high alignment with expert pedagogical standards. To mitigate persistent risks like hallucination and ensure alignment with course-specific context, we advocate for a "teacher-in-the-loop" implementation. Finally, we abstract our methodology into a task-agnostic evaluation framework, advocating for a shift in the development of educational LLM tools from ad-hoc, post-deployment testing to a quantifiable, pre-deployment validation process.
The rapid advancement of Large Language Models (LLMs) has outpaced the scalability of traditional evaluation benchmarks, which remain heavily dependent on labor-intensive expert curation. We address this bottleneck with Conv-to-Bench, a multi-stage framework that automatically transforms authentic multi-turn user-assistant dialogues into structured, verifiable requirement checklists. By leveraging the "instructional evolution" found in real-world conversational logs, our approach deconstructs fragmented user intent into consolidated instructions and binary evaluation criteria. Applied to the programming domain, Conv-to-Bench produces evaluation sets that demonstrate near-perfect alignment with human-authored standards like BigCodeBench, achieving Spearman correlations of up to ρ = 1.000 with significantly lower computational overhead. Validation of the LLM-as-a-judge framework further confirms its reliability, with the primary evaluator achieving substantial agreement with human-verified ground truth (κ = 0.705). Our comprehensive ablation studies reveal that while multi-turn interactions capture the iterative evolution of user intent, instruction-centric extraction provides a more robust foundation. Ultimately, Conv-to-Bench provides a scalable, cost-effective paradigm for maintaining high-fidelity evaluation standards as user-centric AI applications continue to diversify.
Victor M. dos Santos, Andre C. Castro, Samuel L. de S. Toledo +5
Institute of Mathematics and Computer Science, University of São Paulo, Brazil · HUG Labs, Brazil · Institute of Informatics, Federal University of Goiás, Brazil +1