Amplifiers or Equalizers? A Longitudinal Study of LLM Evolution in Software Engineering Project-Based Learning

• URL: http://arxiv.org/abs/2511.23157v1
• Date: Fri, 28 Nov 2025 13:05:23 GMT
• Title: Amplifiers or Equalizers? A Longitudinal Study of LLM Evolution in Software Engineering Project-Based Learning
• Authors: Hana Kataoka, Jialong Li, Yutaka Matsuno,
• Abstract summary: This paper introduces a two-year longitudinal study comparing a 2024 (using early free LLMs, $n$=48) and 2025 (using the latest paid LLMs, $n$=46) cohort.<n>Our findings suggest the latest powerful LLMs' dual role: they act as "equalizers," boosting average performance even for programming-weak students.
• Score: 1.1035164071581713
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As LLMs reshape software development, integrating LLM-augmented practices into SE education has become imperative. While existing studies explore LLMs' educational use in introductory programming or isolated SE tasks, their impact in more open-ended Project-Based Learning (PBL) remains unexplored. This paper introduces a two-year longitudinal study comparing a 2024 (using early free LLMs, $n$=48) and 2025 (using the latest paid LLMs, $n$=46) cohort. Our findings suggest the latest powerful LLMs' dual role: they act as "equalizers," boosting average performance even for programming-weak students, providing opportunities for more authentic SE practices; yet also as "amplifiers," dramatically widening absolute performance gaps, creating new pedagogical challenges for addressing educational inequities.

Related papers

• LLM4VV: Evaluating Cutting-Edge LLMs for Generation and Evaluation of Directive-Based Parallel Programming Model Compiler Tests [7.6818904666624395]
  This paper proposes a dual-LLM system and experiments with the usage of LLMs for the generation of compiler tests.<n>It is evident that LLMs possess the promising potential to generate quality compiler tests and verify them automatically.
  arXiv  Detail & Related papers  (2025-07-29T02:34:28Z)
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
  Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.<n>Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.<n>We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-04T17:26:58Z)
• Whose ChatGPT? Unveiling Real-World Educational Inequalities Introduced by Large Language Models [3.005864877840858]
  ChatGPT and other similar tools have prompted tremendous public excitement and experimental effort about the potential of large language models (LLMs) to improve learning experience and outcomes. However, little research has systematically examined the real-world impacts of LLM availability on educational equity. We analyze 1,140,328 academic writing submissions from 16,791 college students across 2,391 courses between 2021 and 2024 at a public, minority-serving institution in the US. We find that students' overall writing quality gradually increased following the availability of LLMs and that the writing quality gaps between linguistically advantaged and disadvantaged students became increasingly narrower
  arXiv  Detail & Related papers  (2024-10-29T17:35:46Z)
• A Survey Study on the State of the Art of Programming Exercise Generation using Large Language Models [0.0]
  This paper analyzes Large Language Models (LLMs) with regard to their programming exercise generation capabilities. Through a survey study, we defined the state of the art, extracted their strengths and weaknesses and proposed an evaluation matrix.
  arXiv  Detail & Related papers  (2024-05-30T15:49:34Z)
• A Survey on Self-Evolution of Large Language Models [116.54238664264928]
  Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. To address this issue, self-evolution approaches that enable LLMs to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing.
  arXiv  Detail & Related papers  (2024-04-22T17:43:23Z)
• Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing [56.75702900542643]
  We introduce AlphaLLM for the self-improvements of Large Language Models.<n>It integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop.<n>Our experimental results show that AlphaLLM significantly enhances the performance of LLMs without additional annotations.
  arXiv  Detail & Related papers  (2024-04-18T15:21:34Z)
• Large Language Models: A Survey [66.39828929831017]
  Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks.<n>LLMs' ability of general-purpose language understanding and generation is acquired by training billions of model's parameters on massive amounts of text data.
  arXiv  Detail & Related papers  (2024-02-09T05:37:09Z)
• Rethinking Interpretability in the Era of Large Language Models [76.1947554386879]
  Large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks. The capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human. These new capabilities raise new challenges, such as hallucinated explanations and immense computational costs.
  arXiv  Detail & Related papers  (2024-01-30T17:38:54Z)
• An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project [1.433758865948252]
  Large Language Models (LLMs) represent a leap in artificial intelligence, excelling in tasks using human language(s) In this paper, we analyze the AI-generated code, prompts used for code generation, and the human intervention levels to integrate the code into the code base. Our findings suggest that LLMs can play a crucial role in the early stages of software development.
  arXiv  Detail & Related papers  (2024-01-29T14:32:32Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.