paper-with-me

Papers

Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents

2026-08-06 · Yuanhong Jiang, Jingjie Zou, Zhenghong Lin, Xusheng Yu, Qiqi Huang, Shuai Jia, Shijie Dai arxiv

Investment competence is inherently personalized: the same market evidence can justify different actions for investors with different goals, horizons, portfolios, and risk boundaries. Yet financial LLMs are evaluated either by static question answering or by terminal profit and loss. The former omits agency; the latter cannot reveal whether a profitable action was grounded, profile-consistent, or merely lucky. We ask whether the community is using the wrong ruler for consequential agents. We introduce \textsc{InvestLogicBench}, a process-native benchmark containing 201,247 documented decisions from 151 real-world investors. Each episode instantiates a \textbf{P$\rightarrow$E$\rightarrow$R$\rightarrow$D$\rightarrow$O} trace: investor \textit{Profile}, observable market \textit{Events}, investment \textit{Reasoning}, executable \textit{Decision}, and delayed \textit{Outcome}. The release includes profile construction, point-in-time event binding, structured logic, horizons, outcomes, and post-mortems, and supports comprehension, profile-conditioned generation, and end-to-end replay. Across four leading LLMs, logical plausibility remains near 4/5 while event grounding is only 0.8--2.8/5; return and process quality also disagree. These results expose polished but weakly grounded reasoning that outcome-only evaluation hides. We further argue that P$\rightarrow$E$\rightarrow$R$\rightarrow$D$\rightarrow$O should be a data-system interface, requiring versioned profiles, temporal provenance, inspectable retrieval, decision ledgers, and replayable outcomes. Finance is our stress test for a broader class of personalized, consequential agents.

📄 PDF Abstract BibTeX arXiv:2608.06108

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective

2025-03-24 · Changlun Li, Yao Shi, Yuyu Luo, Nan Tang

Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but their effectiveness in financial decision-making remains inadequately evaluated. Current benchmarks primarily assess LLMs…

Decision Making

Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation

2025-05-22 · Zonghan Wu, Junlin Wang, Congyuan Zou, Chenhan Wang 외

Generative AI, particularly large language models (LLMs), is beginning to transform the financial industry by automating tasks and helping to make sense of complex financial information. One especially promising use case…

Financial AnalysisLogical Reasoning

Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking

2025-05-16 · Changlun Li, Yao Shi, Chen Wang, Qiqi Duan 외

Large Language Models (LLMs) have demonstrated notable capabilities across financial tasks, including financial report summarization, earnings call transcript analysis, and asset classification. However, their real-world…

BenchmarkingManagement

Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain

2026-05-09 · Xiaoyu Hu, Jinman Zhao arxiv

Large language models (LLMs) are increasingly deployed in financial contexts, raising critical concerns about reliability, alignment, and susceptibility to adversarial manipulation. While prior finance-related benchmarks…

PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction

2025-12-31 · Bohan Liang, Zijian Chen, Qi Jia, Kaiwei Zhang 외 arxiv

Stock prediction, a subject closely related to people's investment activities in fully dynamic and live environments, has been widely studied. Current large language models (LLMs) have shown remarkable potential in vario…

Stock Price Prediction