发表机构
The Overlake School; Edwards Vacuum Inc.; The University of Memphis（奥弗湖学校; 爱德华兹真空公司; 孟菲斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对基于生产LLM的金融情绪分析成本高问题，提出TriAgent多智能体委员会，按上下文粒度分层，用SDI衡量分歧并路由查询，有批评者平稳期等发现及三个推论，节省成本且效果好。
AI 中文摘要
基于生产大语言模型（LLM）的金融情绪分析面临结构性成本陷阱：大多数查询都很容易分类，但昂贵的云推理器会处理所有查询，且费用随用户数量线性增长。我们提出了TriAgent，这是一个按上下文粒度分层的多智能体委员会，包括词级词汇表（VADER）、句子级领域变换器（FinBERT）和跨句子推理器（Qwen2.5，0.5B - 14B - 4bit，带有Mistral - 7B和Phi - 3.5 - mini跨家族检查）。一个三路语义差异指数（SDI）衡量各粒度之间的成对分歧，并据此路由每个查询。我们的核心发现是批评者平稳期：当将LLM重新用作对较小智能体输出的批评者时，在15亿 - 70亿参数的Qwen模型中F1稳定在约0.87（自展95%置信区间重叠），而相同规模的三人投票降至F1 = 0.66，这是由粒度分层的多样性驱动的。相同的SDI信号产生了三个推论：（i）多语言句子BERT上的共享共识词典以F1 = 0.99从英语缓存中回答95%的中文查询——零边际成本的跨境规范化；（ii）SDI兼作事后LLM幻觉检测器，AUC = 0.90；（iii）SDI单阶段策略在20只股票的回测中获得最佳风险调整回报（夏普比率 = 3.50），优于始终使用FinBERT（1.36）和始终使用LLM（0.11）。在1000万用户规模下，与GPT - 4o - mini基线相比，TriAgent每年节省930万美元。代码、词汇表和SCD已发布。
英文摘要
Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count. We present TriAgent, a multi-agent committee stratified by contextual granularity -- a word-level lexicon (VADER), a sentence-level domain transformer (FinBERT), and a cross-sentence reasoner (Qwen2.5, 0.5B-14B-4bit, with Mistral-7B and Phi-3.5-mini cross-family checks). A three-way Semantic Divergence Index (SDI) measures pairwise disagreement across granularities and routes each query accordingly. Our central finding is the critic plateau: when the LLM is re-tasked as a critic over the smaller agents' outputs, F1 plateaus at ~0.87 across 1.5B-7B Qwen (bootstrap 95% CIs overlap), while a same-size 3-persona vote drops to F1=0.66, which is driven by granularity-stratified diversity. Three corollaries follow from the same SDI signal: (i) a Shared Consensus Dictionary on multilingual sentence-BERT answers 95% of Chinese queries from an English cache at F1=0.99 -- cross-border canonicalization at zero marginal cost; (ii) SDI doubles as a post-hoc LLM-hallucination detector at AUC=0.90; (iii) the SDI single-stage strategy attains the best risk-adjusted return (Sharpe=3.50) on a 20-ticker back-test, dominating both always-FinBERT (1.36) and always-LLM (0.11). At 10M-user scale, TriAgent saves $9.3M/year vs. a GPT-4o-mini baseline. Code, lexicons, and the SCD are released.
