How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding

• URL: http://arxiv.org/abs/2609.11109v1
• Date: Thu, 10 Sep 2026 05:34:47 GMT
• Title: How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding
• Abstract summary: We develop a literature-informed baseline pipeline that enables AI agents to independently code, debate, and reconcile disagreements.<n>Results revealed that coding accuracy depends on factors such as codebook length, qualitative data similarity, and agent disagreement.<n>Our open-source AI discussion dataset and methodological framework lay the groundwork for advancing the design of AI-mediated automated thematic analysis.
• Score: 5.271725890500162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The utility of AI in multi-coder qualitative coding has been widely discussed, yet little empirical evidence exists to delineate the contexts in which it performs reliably. We address this gap by quantifying the effectiveness of multi-agent LLM coding across varied qualitative datasets, revealing key contextual and structural factors that mediate coding outcomes. We developed a literature-informed baseline pipeline that enables AI agents to independently code, debate, and reconcile disagreements. Results revealed that coding accuracy depends on factors such as codebook length, qualitative data similarity, and agent disagreement. Notably, intense and unresolved debates between agents led to higher accuracy. Our analysis showed that while LLMs emulate many human discussion behaviors, they lack adaptive responsiveness to context. From these findings, we offer design recommendations for building automated coding systems. Our open-source AI discussion dataset and methodological framework lay the groundwork for advancing the design of AI-mediated automated thematic analysis.

Related papers

• ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation [54.788849448970154]
  We introduce ClarifyCodeBench, a novel interactive benchmark for evaluating Large Language Models' capability in resolving requirement ambiguity.<n>We conduct a systematic evaluation of six state-of-the-art LLMs using ClarifyCodeBench.<n>Our empirical results yield three critical insights: 1) Capability Decoupling: Strong code generation performance does not inherently translate to effective requirement clarification; 2) The Reasoning Paradox: While increased computational thinking enhances code correctness, it yields marginal gains in identifying ambiguities.
  arXiv  Detail & Related papers  (2026-07-01T09:58:59Z)
• Factors Influencing the Quality of AI-Generated Code: A Synthesis of Empirical Evidence [1.4465033892011254]
  The rapid adoption of AI-assisted code generation tools is transforming software development practices.<n>Concerns regarding the quality, reliability, and security of AI-generated code are increasingly reported in both academia and industry.
  arXiv  Detail & Related papers  (2026-03-26T08:06:42Z)
• Disagreement as Data: Reasoning Trace Analytics in Multi-Agent Systems [0.0]
  We propose that reasoning traces generated by large language model (LLM) agents constitute a novel and rich form of process data.<n>We apply cosine similarity to reasoning traces to systematically detect, quantify, and interpret disagreements among agents.
  arXiv  Detail & Related papers  (2026-01-18T23:19:49Z)
• A Survey of Vibe Coding with Large Language Models [93.88284590533242]
  "Vibe Coding" is a development methodology where developers validate AI-generated implementations through outcome observation.<n>Despite its transformative potential, the effectiveness of this emergent paradigm remains under-explored.<n>This survey provides the first comprehensive and systematic review of Vibe Coding with large language models.
  arXiv  Detail & Related papers  (2025-10-14T11:26:56Z)
• CoDA: Agentic Systems for Collaborative Data Visualization [57.270599188947294]
  Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations.<n>Existing approaches, including simple single- or multi-agent systems, often oversimplify the task.<n>We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection.
  arXiv  Detail & Related papers  (2025-10-03T17:30:16Z)
• 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)
• Trust at Your Own Peril: A Mixed Methods Exploration of the Ability of Large Language Models to Generate Expert-Like Systems Engineering Artifacts and a Characterization of Failure Modes [0.0]
  We present results from an empirical exploration, where a human expert-generated SE artifact was taken as a benchmark.<n>We then adopted a two-fold mixed-methods approach to compare AI generated artifacts against the benchmark.<n>We find that while the two-material appear very similar, AI generated artifacts exhibit serious failure modes that could be difficult to detect.
  arXiv  Detail & Related papers  (2025-02-13T17:05:18Z)
• Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights [0.0]
  This paper introduces a novel scoring mechanism called the SBC score.<n>It is based on a reverse generation technique that leverages the natural language generation capabilities of Large Language Models.<n>Unlike direct code analysis, our approach reconstructs system requirements from AI-generated code and compares them with the original specifications.
  arXiv  Detail & Related papers  (2025-02-11T01:12:11Z)
• 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)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• When Do Program-of-Thoughts Work for Reasoning? [51.2699797837818]
  We propose complexity-impacted reasoning score (CIRS) to measure correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct.
  arXiv  Detail & Related papers  (2023-08-29T17:22:39Z)

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.