Related papers: Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development

Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development

URL: http://arxiv.org/abs/2607.06101v1
Date: Tue, 07 Jul 2026 10:14:44 GMT
Title: Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development
Abstract summary: We argue that incidental learning will not re-emerge on its own and must be consciously designed back into developer-agent interactions.<n>We present "SHIELD", a multi-agent system grounded in the notion of "agents that teach"<n>We envision a path toward learning-aware development environments where productivity and learning are complementary, not competing.
Score: 1.6193916818014198
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: AI coding agents are rapidly reshaping how software is built, with developers increasingly delegating substantial coding tasks to autonomous agents in pursuit of higher productivity. While these gains are real, they come at the cost of incidental learning. Developers historically acquired informal knowledge through effortful problem-solving, and this has long shaped how software engineering expertise develops. However, with over-reliance on agentic coding, unpracticed skills could atrophy silently over time. As this learning pathway is short-circuited, developers risk silently accruing Knowledge Debt, a developer-level analogue of Technical Debt, where changes the agent executes that the developer cannot fully understand accrue over time. In this paper, we argue that incidental learning will not re-emerge on its own and must be consciously designed back into developer-agent interactions, and propose six design principles to guide such systems. We then present "SHIELD", a multi-agent system grounded in the notion of "agents that teach", that operationalizes these principles by leveraging the AI coding agent's own reasoning to surface contextual, out-of-band learning moments without disrupting developer flow. Through this work, we envision a path toward learning-aware development environments where productivity and learning are complementary, not competing.

Related papers

PRAXIS: Graph-Grounded Tacit Knowledge for Domain Code Generation [61.752289169878566]
We identify the root cause of the agent's lack of tacit knowledge, including domain-specific business rules, interface contracts, and operational conventions that developers internalize through practice but never document.<n>This knowledge is deeply buried beneath the domain code, across code entities and their dependency relations, and invisible to the agent that lacks it.<n>We propose PRAXIS, a framework that enables agents to extract, represent, and reuse tacit knowledge for domain code generation.
arXiv Detail & Related papers (2026-08-20T08:28:28Z)
AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering [4.609790123179083]
We present textitAgentForge, an immersive learning system in which novices take on one of four software-engineering roles.<n>In each practice session, novices perform their chosen role while AI agents perform the remaining three.<n>In a study with 37 novice developers, participants achieved high task-completion rates with AI-agent support.
arXiv Detail & Related papers (2026-08-04T18:58:18Z)
How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests [5.6795075579540395]
This study aims to characterize agentic pull requests (PR) in comparison to human generated PRs.<n>We first analyze how differences in merge rates between agentic and human generated PRs vary over time.<n>We then identify the types of development tasks where AI coding agents are predominantly applied.
arXiv Detail & Related papers (2026-07-23T21:48:28Z)
AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems [82.01232437066487]
AgentX is a production-deployed multi-agent system that restructures this production function.<n>It autonomously generates, implements, evaluates, and learns from recommendation experiments.<n>AgentX orchestrates four tightly coupled stages in a closed loop.
arXiv Detail & Related papers (2026-06-25T10:42:28Z)
"I'm Not Reading All of That": Understanding Software Engineers' Level of Cognitive Engagement with Agentic Coding Assistants [9.74467739744379]
Over-reliance on AI systems can undermine users' critical thinking and promote complacency.<n>In software engineering, agentic coding assistants (ACAs) are rapidly becoming embedded in everyday development.
arXiv Detail & Related papers (2026-03-15T05:03:20Z)
Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning [84.70211451226835]
Large Language Model (LLM) Agents are constrained by a dependency on human-curated data.<n>We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data.<n>Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks.
arXiv Detail & Related papers (2025-11-20T05:01:57Z)
Agentsway -- Software Development Methodology for AI Agents-based Teams [4.226647687395254]
"Agentsway" is a novel software development framework designed for ecosystems where AI agents operate as first-class collaborators.<n>The framework defines distinct roles for planning, prompting, coding, testing, and fine-tuning agents.<n>Agentsway represents a foundational step toward the next generation of AI-native, self-improving software development methodologies.
arXiv Detail & Related papers (2025-10-26T11:58:42Z)
Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development [8.821206496273842]
We identify challenges from both software and large language models perspectives.<n>We propose the Code Digital Twin, a framework that models both the physical and conceptual layers of software.<n>Our vision positions it as a bridge between AI advancements and enterprise software realities.
arXiv Detail & Related papers (2025-10-18T08:17:54Z)
Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [60.04362496037186]
We present the first controlled study of developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants.<n>Our results show agents can assist developers in ways that surpass copilots.
arXiv Detail & Related papers (2025-07-10T20:12:54Z)
Software Reuse in the Generative AI Era: From Cargo Cult Towards AI Native Software Engineering [2.7808182112731537]
We discuss the implications of AI-assisted generative software reuse in the context of emerging "AI native" software engineering.<n>This paper defines a tentative research agenda and call to action for tackling some of the central issues associated with this approach.
arXiv Detail & Related papers (2025-06-22T08:09:25Z)
Agent-Driven Automatic Software Improvement [55.2480439325792]
This research proposal aims to explore innovative solutions by focusing on the deployment of agents powered by Large Language Models (LLMs) The iterative nature of agents, which allows for continuous learning and adaptation, can help surpass common challenges in code generation. We aim to use the iterative feedback in these systems to further fine-tune the LLMs underlying the agents, becoming better aligned to the task of automated software improvement.
arXiv Detail & Related papers (2024-06-24T15:45:22Z)
Experiential Co-Learning of Software-Developing Agents [83.34027623428096]
Large language models (LLMs) have brought significant changes to various domains, especially in software development. We introduce Experiential Co-Learning, a novel LLM-agent learning framework. Experiments demonstrate that the framework enables agents to tackle unseen software-developing tasks more effectively.
arXiv Detail & Related papers (2023-12-28T13:50:42Z)

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