{
  "id": 7079,
  "url": "https://arxiv.org/abs/2603.17417v2",
  "title": "Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)",
  "summary": "Current Large Language Models (LLMs) are gradually exploited in practically valuable agentic workflows such as Deep Research, E-commerce recommendation, and job recruitment. In these applications, LLMs need to select some optimal solutions from massive candidates, which we term as \\textit{LLM-as-a-Recommender} paradigm. However, the reliability of using LLM agents for recommendations is underexplored. In this work, we introduce a \\textbf{Bias} \\textbf{Rec}ommendation \\textbf{Bench}mark (\\textbf{",
  "authors": "Zichen Tang, Zirui Zhang, Qian Wang, Zhenheng Tang, Bo Li, Xiaowen Chu",
  "category": "research",
  "topics": "bias-fairness,jobs-economy,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-18T06:50:48.000Z",
  "fetched_at": "2026-07-14T16:32:59.163Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7079",
  "original_url": "https://arxiv.org/abs/2603.17417v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}