{
  "id": 17351,
  "url": "https://arxiv.org/abs/2608.06108v1",
  "title": "Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents",
  "summary": "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 int",
  "authors": "Yuanhong Jiang, Jingjie Zou, Zhenghong Lin, Xusheng Yu, Qiqi Huang, Shuai Jia, Shijie Dai",
  "category": "research",
  "topics": "agents-autonomy,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T14:41:56.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/17351",
  "original_url": "https://arxiv.org/abs/2608.06108v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}