{
  "absUrl": "https://arxiv.org/abs/2610.02181",
  "arxivId": "2610.02181",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Haibo Wang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Jiteng Mu"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Jialu Li"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Jingru Yi"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yuanjun Xiong"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Jianming Zhang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Lifu Huang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Mingze Xu"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.02181",
  "originalTitle": "OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning",
  "pdfUrl": "https://arxiv.org/pdf/2610.02181.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}