English(EN) Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method

新基准和智能体方法推动空地协同目标搜索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员推出 AGOS-Bench，这是一个旨在评估视觉语言模型（VLM）在空地目标搜索场景中协同能力的新基准。该基准连同配套数据集和名为 AGOS-Agent 的智能体方法，旨在促进需要无人机（UAV）和无人地面车辆（UGV）之间协调的任务的研究。AGOS-Agent 具有无需训练且支持工具增强的特点，已在多个 VLM 的成功率和决策步数方面取得了显著改进，特别是 Gemini 3.6 Flash 取得了显著进步。 AI

影响这项研究可能催生更复杂的自主系统，能够在现实环境中执行复杂、协同的搜索和验证任务。

排序理由该条目是一篇 arXiv 论文，介绍了一个用于特定 AI 任务的新基准、数据集和智能体方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇 arXiv 论文，介绍了一个用于特定 AI 任务的新基准、数据集和智能体方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Boao Yu, Zimo Chen, Junreng Rao, Yue Hu, Zhengqiu Zhu, Yong Zhao, Rusheng Ju · 2026-09-10 04:00

迈向具身空地协同目标搜索：基准、数据集与智能体方法

arXiv:2609.08402v1 Announce Type: cross Abstract: Air-Ground Object Search (AGOS) in urban environments is a challenging embodied task, which requires an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV) to jointly search for and verify a specified target vehicle…

本文如何被排名

报道来源 [1]

迈向具身空地协同目标搜索：基准、数据集与智能体方法

相关实体

相关话题