{
  "id": 3401,
  "url": "https://arxiv.org/abs/2606.00593v2",
  "title": "SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering",
  "summary": "Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensive set of valid answers, a setting known as Multi-Answer QA. This setting raises two challenges: fine-grained credit assignment over long search trajectories and reward alignment f",
  "authors": "Qiming Shi, Zhaolu Kang, Yunfan Zhou, Di Weng, Yingcai Wu",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-30T07:47:42.000Z",
  "fetched_at": "2026-07-14T16:30:14.369Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3401",
  "original_url": "https://arxiv.org/abs/2606.00593v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}