研究温度与角色对大模型协作编码的影响，发现未显著提升准确率

Large Language Models (LLMs) enable new possibilities for qualitative research at scale, including annotation and qualitative coding of educational data. While LLM-based multi-agent systems (MAS) can emulate human coding workflows, their benefits over single LLM agents for coding remain poorly understood. To that end, we conducted an experimental study of how persona and temperature of component agents of a MAS shapes consensus-building and coding accuracy for dialog segments. LLMs were prompted to code these segments deductively using a mature codebook with 8 codes and high inter-rater reliability derived from prior research. Our open-source MAS mirrors deductive human coding through structured agent discussion and consensus arbitration. Using six open-source LLMs (with 3 to 32 billion parameters) and 18 experimental configurations, we analyze over 77,000 coding decisions against a gold-standard dataset of human-annotated transcripts from online math tutoring sessions facilitated by educational software. Temperature significantly impacted whether and when consensus was reached across all six LLMs. MAS with multiple personas (including neutral, assertive, or empathetic) significantly delayed consensus in four out of six LLMs compared to uniform personas. In three of those LLMs, higher temperatures significantly diminished the effects of multiple personas on consensus. However, neither temperature nor persona pairing led to robust improvements in coding accuracy. Single agents matched or outperformed MAS consensus in most conditions. Qualitative analysis of MAS collaboration and coding disagreement may, however, improve codebook design and human-AI coding.