Skip to content
AI Atlas
PaperActive

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

arxiv.org/abs/2609.11109

quality89

Updated 2 h ago · first seen 12 Sept 2026

paper_01M29X34VNHTXGYVDEEQH512MC

Published
12 Sept 2026
T1 · 2 h ago
arXiv
2609.11109
T1 · 2 h ago
Category
cs.HC
T1 · 2 h ago

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.

Authors 2

Jeongyeon Kim, John Mitchell

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

arXiv id
2609.11109

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Categories
cs.AI, cs.HC

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Primary category
cs.HC

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Published
12 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

2 h ago

Conflicts

None