Bio-pharmaceutical innovation has shifted: many new drug assets now originate outside the United States and are disclosed primarily via regional, non-English channels. Recent data suggests that over 85% of patent filings originate outside the U.S., with China accounting for nearly half of the global total. A growing share of scholarly output is also non-U.S. Industry estimates put China at 30% of global drug development, spanning 1,200+ novel candidates. In this high-stakes environment, failing to surface "under-the-radar" assets creates multi-billion-dollar risk for investors and business development teams, making asset scouting a coverage-critical competition where speed and completeness drive value. Yet today's Deep Research AI agents still lag human experts in achieving high recall discovery across heterogeneous, multilingual sources without hallucination. We propose a benchmarking methodology for drug asset scouting and a tuned, tree-based self-learning Bioptic Agent aimed at complete, non-hallucinated scouting. We construct a challenging completeness benchmark using a multilingual multi-agent pipeline: complex user queries paired with ground-truth assets that are largely outside U.S.-centric radar. To reflect real-deal complexity, we collected screening queries from expert investors, BD, and VC professionals and used them as priors to conditionally generate benchmark queries. For grading, we use LLM-as-judge evaluation calibrated to expert opinions. On this benchmark, our Bioptic Agent achieves 79.7% F1 score, outperforming Claude Opus 4.6 (56.2%), Gemini 3 Pro + Deep Research (50.6%), OpenAI GPT-5.2 Pro (46.6%), Perplexity Deep Research (44.2%), and Exa Websets (26.9%). Performance improves steeply with additional compute, supporting the view that more compute yields better results.

翻译：生物制药创新格局已发生转变：大量新药资产如今源自美国境外，且主要通过区域性非英文渠道披露。最新数据显示，超过85%的专利申请来自美国以外，其中中国占全球总量的近一半。海外学术产出的占比亦持续增长。据行业估计，中国占全球药物开发的30%，涵盖1200余种创新候选药物。在这种高风险环境下，未能发现“隐秘”资产将为投资者及业务拓展团队带来数十亿美元的风险，使得资产搜寻成为关乎覆盖率的关键竞争——速度与完整性直接决定价值。然而，当前深度研究AI智能体在跨异构多语种实现高召回率发现时，仍落后于人类专家，且存在幻觉问题。我们提出了一种针对药物资产搜寻的基准测试方法论，以及一种经过调优的基于树的自主学习双视野智能体，旨在实现完整且无幻觉的搜寻。我们通过构建多语言多智能体流程，将复杂用户查询与主要位于美国核心视野之外的真实资产配对，建立了一套具有挑战性的完整性基准。为反映真实交易复杂性，我们收集了来自专家投资者、业务拓展及风险投资专业人士的筛选查询，并将其作为先验条件以生成基准查询。在评分环节，我们采用经过专家意见校准的LLM作为评判模型。在该基准上，我们的双视野智能体取得了79.7%的F1分数，超越了Claude Opus 4.6（56.2%）、Gemini 3 Pro +深度研究（50.6%）、OpenAI GPT-5.2 Pro（46.6%）、Perplexity深度研究（44.2%）以及Exa Websets（26.9%）。随着计算资源的增加，性能显著提升，这支持了“更多计算资源带来更优结果”的观点。