Agentic AI-assisted coding offers a unique opportunity to instill epistemic grounding during software development

• URL: http://arxiv.org/abs/2604.21744v1
• Date: Thu, 23 Apr 2026 14:50:35 GMT
• Title: Agentic AI-assisted coding offers a unique opportunity to instill epistemic grounding during software development
• Abstract summary: Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic software development using agent scaffolds.<n>One current trend is utilizing documents beyond this plan document, such as project and method-scoped documents.<n>Here we propose GROUNDING.md, a community-governed, field-scoped grounding document.
• Score: 0.02058747290260746
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic software development using agent scaffolds where the human developer creates a plan that agentic AIs implement. One current trend is utilizing documents beyond this plan document, such as project and method-scoped documents. Here we propose GROUNDING.md, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example. This explicit field-scoped grounding document encodes Hard Constraints (non-negotiable validity invariants empirically required for scientific correctness) and Convention Parameters (community-agreed defaults) that override all other contexts to enforce validity, regardless of what the user prompts. In practice, this will empower a non-domain expert to generate code, tools, and software that have best practices baked in at the ground level, providing confidence to the software developer but also to those reviewing or using the final product. Undoubtedly it is easier to have agentic AIs adhere to guidelines than humans, and this opportunity allows for organizations to develop epistemic grounding documents in such a way as to keep domain experts in the loop in a future of democratized generation of bespoke software solutions.

Related papers

• ''You Can't Open an LLM With a Screwdriver'': The De-Democratization of Software [10.424169529626694]
  Claims that generative AI will soon write all of the code have led to predictions that programming is nearing its end.<n>This vision paper argues that AI does not eliminate software engineering expertise but shifts where that expertise becomes most critical.
  arXiv  Detail & Related papers  (2026-08-25T15:35:40Z)
• On Automated and Explainable Provenance of AI-Generated Code [56.818202904805446]
  We argue that the next generation of CodeGenAI tools must be built on a foundation of explainable provenance.<n>We describe a research program combining large-scale empirical studies with post-hoc causal and interpretability techniques.
  arXiv  Detail & Related papers  (2026-08-03T14:50:31Z)
• LLMoxie: Exploring Agentic AI for Scientific Software Development [0.2708918306110244]
  Report on twenty months of practice at a university-based research software engineering (RSE) center, where RSEs embedded across astronomy, earth and climate science, agriculture, and health projects worked to close this gap.<n>We describe the recurring infrastructure, governance, and process challenges of adopting Agentic AI inside a multi-domain RSE center, describe the platform and plugin design, and distill operational lessons from real scientific software deployments.
  arXiv  Detail & Related papers  (2026-07-02T18:46:27Z)
• AI for Auto-Research: Roadmap & User Guide [107.0834449839233]
  We present an end-to-end analysis of AI across the complete research lifecycle.<n>We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy.<n>We show that greater automation can obscure rather than eliminate failure modes.
  arXiv  Detail & Related papers  (2026-05-18T17:08:26Z)
• Bridging the Gap on AI-Assisted Scientific Software Development Through Transparency and Traceability [4.466942018046944]
  Researchers are already using large language models to write code, generate test cases, and draft documentation.<n>This ad hoc, ungoverned use of AI represents a systemic risk to scientific software quality.<n>This paper proposes guidance for AI-assisted code development in the context of strict software quality assurance.
  arXiv  Detail & Related papers  (2026-05-17T22:08:52Z)
• Operationalizing Ethics for AI Agents: How Developers Encode Values into Repository Context Files [11.207503404473842]
  This vision paper investigates how ethics and values are already being translated for AI agents into actionable instructions that shape agent behavior.<n>We find that developers are already embedding guidance related to fairness, accessibility, sustainability, tone, and privacy.
  arXiv  Detail & Related papers  (2026-05-07T02:03:36Z)
• Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization [69.36509281190662]
  Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck.<n>We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design.<n>We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions.
  arXiv  Detail & Related papers  (2025-12-02T18:42:26Z)
• Context Engineering for AI Agents in Open-Source Software [13.236926479239754]
  GenAI-based coding assistants have disrupted software development.<n>Their next generation is agent-based, operating with more autonomy and potentially without human oversight.<n>One challenge is to provide AI agents with sufficient context about the software projects they operate in.
  arXiv  Detail & Related papers  (2025-10-24T12:55:48Z)
• Rapid Development of Omics Data Analysis Applications through Vibe Coding [0.0]
  I demonstrate that modern large language models (LLMs) and autonomous coding agents can dramatically lower this barrier.<n>I used Vibe coding to create a fully functional data analysis website capable of performing standard tasks.<n>The entire application, including user interface, backend logic, and data upload pipeline, was developed in less than ten minutes using only four natural-language prompts.
  arXiv  Detail & Related papers  (2025-10-10T19:06:27Z)
• CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection [60.52240468810558]
  We introduce CoCoNUTS, a content-oriented benchmark built upon a fine-grained dataset of AI-generated peer reviews.<n>We also develop CoCoDet, an AI review detector via a multi-task learning framework, to achieve more accurate and robust detection of AI involvement in review content.
  arXiv  Detail & Related papers  (2025-08-28T06:03:11Z)
• 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)
• Can We Trust AI Agents? A Case Study of an LLM-Based Multi-Agent System for Ethical AI [10.084913433923566]
  AI-based systems impact millions by supporting diverse tasks but face issues like misinformation, bias, and misuse.<n>This study examines the use of Large Language Models (LLM) for AI ethics in practice.<n>We design a prototype, where agents engage in structured discussions on real-world AI ethics issues from the AI Incident Database.
  arXiv  Detail & Related papers  (2024-10-25T20:17:59Z)
• Software Engineering Methods For AI-Driven Deductive Legal Reasoning [2.95701410483693]
  We show how principled software engineering techniques can enhance AI-driven legal reasoning of complex statutes. We show how it is possible to apply principled software engineering techniques to unlock new applications in automated meta-reasoning.
  arXiv  Detail & Related papers  (2024-04-15T15:33:29Z)
• Custom Developer GPT for Ethical AI Solutions [1.2691047660244337]
  This project aims to create a custom Generative Pre-trained Transformer (GPT) for developers to discuss and solve ethical issues through AI engineering. The use of such a tool can allow practitioners to engineer AI solutions which meet legal requirements and satisfy diverse ethical perspectives.
  arXiv  Detail & Related papers  (2024-01-19T20:21:46Z)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)

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.