这篇论文出个黑盒诊断，看LLM集体输出分散时是不是真改观点，结果GPT和Gemini相反：Gemini 94%在复读，GPT 24%。
一项新研究提出Coherence Index（CI）与Meta-Predictive Clarity System（MPCS），用于黑盒诊断LLM集体的输出分散与认知修订耦合。研究在gpt-4o-mini和gemini-2.5-flash上构建5-agent集体，每种条件运行310个配对。在gpt-4o-mini上，条件异议将虚假前提恢复率提高17.7点，而静态人格多样性使其降低8.1点。在gemini-2.5-flash上，相同干预几乎无增益（26.1% vs 27.1%），尽管输出分散度确实下降。机制标注显示，Gemini的94%响应为重新表述而非承认，GPT为24%。
When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Coupling Diagnostic for Machine Collectives
Collective intelligence research treats disagreement as evidence of epistemic diversity: if agents express different views, the group should retain capacity to revise. In LLM collectives this proxy can break: agents can produce diverse-looking arguments while preserving the same conclusion. We operationalize dispersion-revision coupling: the degree to which an intervention that verifiably increases the dispersion of a collective's outputs in embedding space is accompanied by genuine revision of its epistemic stance rather than premise-preserving reformulation. The diagnostic is black-box: it operates on generated text alone and makes no claims about the internal representations of the generating models. Two channels are measured independently: an output channel, the Coherence Index (CI), verifies that the intervention changed output dispersion; an epistemic channel, per-turn stance annotation, measures whether the collective revised. We propose CI with the Meta-Predictive Clarity System (MPCS), which inserts a Re-Differentiation Protocol (RDP) when outputs over-converge, as a reusable method for estimating this coupling regime. We evaluate five-agent collectives from two configurations (gpt-4o-mini and gemini-2.5-flash; 310 paired episodes per condition). On gpt-4o-mini, conditional dissent improves false-premise recovery by +17.7 points (p<1e-6) while static persona diversity harms recovery (-8.1, p=.007). On gemini-2.5-flash, the same intervention at a comparable budget yields no gain (26.1% vs 27.1%, p=.84) despite a verified dispersion drop; the two treatment effects differ from each other (z=3.79, p<.001). Mechanism tagging shows Gemini preserves the false premise via intra-framework dissent: 94% of tagged post-RDP responses reformulate rather than concede (vs 24% on GPT). We recommend reporting per-intervention stance shift and premise-preservation rate alongside accuracy.