arXiv cs.AI· Yanbin Yin, Chuyu Xu, Liqin Ye, Jing Peng, Chao Zhang·· 14 小时前AI 评分34
EPSBench：面向 LLM 智能体盈利预测的基准测试
EPSBench: Benchmarking LLM Agents for Earnings Forecasting
AI 导读
研究者推出 EPSBench，用 86 家美国公司的 149 个公司-季度样本评测 LLM 智能体预测季度 EPS 的能力：智能体阅读财报、电话会议记录与新闻，估算利润表驱动项并附引用证据，再由统一会计计算器换算为 GAAP 稀释每股收益。
正文 · 原文
Abstract:Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that produce a company's reported earnings. We introduce EPSBench, a benchmark for studying this ability across 149 firm-quarters from 86 US companies. Agents read a fixed collection of filings, earnings-call transcripts, and news, then estimate company-specific income-statement drivers with cited evidence. A shared accounting calculator converts these estimates into GAAP diluted earnings per share (EPS), providing a common basis for comparing forecast assumptions. We evaluate six models under a common harness, assessing point forecast error relative to date-matched analyst consensus and checking whether their prediction intervals achieve the stated coverage. Three models show no detectable paired difference in point forecast error from consensus, and three have higher error. Across all six models, nominal 80% intervals contain reported EPS in only 37--70% of runs that return an interval, and most misses fall above the upper bound because the forecasts run low. The driver records trace most of the error gap between models to operating-income estimates.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.38293 [cs.CL] |
| (or arXiv:2610.38293v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38293 arXiv-issued DOI via DataCite |
Submission history
From: Liqin Ye [view email]
[v1]
Wed, 28 Oct 2026 05:24:11 UTC (303 KB)
来源：arXiv cs.AI · arxiv.org