{
  "id": 3326,
  "url": "https://arxiv.org/abs/2606.01441v1",
  "title": "Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts",
  "summary": "Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve intent while triggering commonsense hallucinations. This vulnerability is urgent, as LLMs are rapidly integrated into safety-critical domains where factual reliability is non-negotiable. Existing attack methods either lack efficiency or fail to capture the adaptive strategies of real-world adversaries. We propose an A*-inspired Factual Error Induct",
  "authors": "Boxuan Wang, Zhuoyun Li, Xiaowei Huang, Yi Dong",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-31T20:20:53.000Z",
  "fetched_at": "2026-07-14T16:30:09.962Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3326",
  "original_url": "https://arxiv.org/abs/2606.01441v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}