跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 26 天前AI 評分49

Investor's Last Exam:AI 智能體能否在不預知未來的情況下進行股票投資?

Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?

AI 導讀

Investor's Last Exam(ILE)以凍結的決策時點證據評估金融智能體的端到端股票研究,結果顯示頂尖模型擅長研究,但預測和投資判斷仍有不足。評估涵蓋 86 項任務,GPT-6 Astra 和 Claude Opus 5.5 總分分別為 68.1 和 66.9(滿分 100);Astra 的 Forecast & Model 得分為 52.5。

正文

Image 1: Hugging Face's logoHugging Face


Papers

arxiv:2610.38342

Copy markdown

Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?

Published on Oct 28

·Submitted byImage 2 caiyuchenon Oct 30

- [x] Upvote 2

  • Image 3
  • Image 4

Authors:

Huangfei Jiang,

Anning Hu,

Kai Sheng,

Yuchen Cai,

Rui Ge,

Xiangyu Kong,

Jianghao Lin,

Shuzi Chen,

Jiyi Weng,

Junchi Yan

Abstract

Investor's Last Exam evaluates financial agents on end-to-end equity research using frozen evidence, expert criteria, and dependency graphs, revealing that top models excel at research but fail at forecasting and investment judgments.

Generated by thinkingmachines/Inkling-Small

Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financial knowledge, research workflows, or forecasting, but evaluating the full research process requires a strictly frozen information set and professional evaluation criteria. We introduce Investor's Last Exam (ILE), an equity-research benchmark led by experienced buy-side investors and fund managers. Its three components are a versioned financial database spanning 3.43 million document versions and nine source categories, supplemented by structured market data, with validated timestamps governing retrieval and computation; a task taxonomy organized around professional analyst deliverables; and an expert-led framework linking scoring criteria to sources, calculations, and assumptions through financial dependency graphs. Evaluation spans 86 assignments and jointly assesses research quality, forecast accuracy, and simulated investment performance. GPT-6 Astra and Claude Opus 5.5 lead overall at 68.1 and 66.9 out of 100, yet even Astra scores only 52.5 on Forecast & Model. Our results show that even state-of-the-art models fail to translate overall research capability into predictive performance. ILE shifts the evaluation unit from isolated capabilities to the evidence--assumption--judgment chain, allowing researchers to locate where analytical advantages fail to translate into forecasts and investment judgments, and providing a traceable, diagnostic foundation for training and evaluating financial agents.

View arXiv pageView PDFProject pageGitHubAdd to collection

Community

Image 5

caiyuchen

Paper submitter21 minutes ago

Evaluating forecasting capability usually means waiting for outcomes to materialize — months, sometimes years — during which market conditions, fundamentals, and the information environment shift enough that scores can no longer be cleanly attributed to the model; moreover, most work in LLM4Finance has focused on the research stage rather than the investment stage, which is where the field's core objective lies. ILE asks whether an agent, using only what was visible at decision time, can independently complete the full chain from evidence to assumptions to forecast. To answer it, we built a versioned corpus (3.43M document versions, 1.52TB, 9 source classes) that enforces the cutoff across the entire toolchain — specify a timestamp and you get exactly the versions visible at that moment — and organized 86 assignments around buy-side analyst deliverables, with rubrics anchored to sources and reproducible calculations through financial dependency graphs. Among current SOTA systems, Astra scores 78.9 on Research & Evidence but only 52.5 on Forecast & Model, and ordering by realized outcomes puts DeepSeek V4.1 Flash ahead (40.3 vs 37.7): today's models are very good at organizing evidence of what has already happened into coherent analysis, and not yet good at turning that analysis into judgment about what has not. For me, the longer-term significance is on the training side — once the time boundary is a mechanism, historical timestamps become a re-samplable environment for large-scale domain RL, with evaluation and training sharing one environment.

Reply

Edit Preview

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Comment ·Sign up or log in to comment

- [x] Upvote 2

  • Image 6
  • Image 7

Get this paper in your agent:

hf papers read 2610.38342

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.38342 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.38342 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.38342 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

System theme

Company

TOSPrivacyAboutCareers

Website

ModelsDatasetsSpacesPricingDocs

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co