{"ID":2922150,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T17:28:21.356497881Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00820","arxiv_id":"2606.00820","title":"Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate","abstract":"Multi-agent debate (MAD) is a promising strategy for improving LLM reasoning, but when agents converge on a shared answer, it is unclear whether that convergence reflects genuine deliberation or social compliance. We show that the conventional answer flip rate conflates three distinct mechanisms: spontaneous instability, stance-induced conformity, and reasoning-induced persuasion. Our three-source decomposition framework isolates each through controlled counterfactual conditions. In the primary MMLU-Pro setting, 37% of agent-question observations change under self-reflection alone, while robustness tests show substantial model-dependent instability across GPQA-Diamond and three model families; strict conformity is 29% in the primary setting and remains predominantly harmful across model replications (57-77% correct-to-wrong). A controlled information-gradient experiment reveals that even vacuous reasoning is associated with 20-39% error adoption among resistant agents, with reasoning-like presentation carrying substantial persuasive weight. Harmful conformity can be predicted from Round 0 features (AUC = 0.79), and risk-targeted intervention reduces it by 13.6 percentage points (p \u003c 0.001). However, without correctness labels or self-reflection controls, reducing peer adoption does not improve accuracy, because harmful and beneficial influence cannot be distinguished.","short_abstract":"Multi-agent debate (MAD) is a promising strategy for improving LLM reasoning, but when agents converge on a shared answer, it is unclear whether that convergence reflects genuine deliberation or social compliance. We show that the conventional answer flip rate conflates three distinct mechanisms: spontaneous instabilit...","url_abs":"https://arxiv.org/abs/2606.00820","url_pdf":"https://arxiv.org/pdf/2606.00820v1","authors":"[\"Xiqi Hao\",\"Zengqing Wu\",\"Yu-Xuan Qiu\",\"Chuan Xiao\",\"Ruiqi Xu\",\"Shuyuan Zheng\",\"Jianbin Qin\"]","published":"2026-05-30T17:41:11Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}