这项研究揭示了AI在科学数据检索中的致命短板，做生物信息学或依赖AI处理数据库的团队值得关注——重复检索工具可能是提升可靠性的关键。
Anthropic最新研究发现，AI智能体在编程任务中表现出色，但在生物学数据检索中可能失败。同一生物学数据请求，即使提示词不变，不同运行结果差异巨大。例如，在埃博拉序列任务中，Claude Sonnet 4一次返回106条序列，另一次返回15条，而正确答案是266条。这种不一致性会改变科学结论，如将疫情起源误判为1922年而非2014年。研究指出，添加可重复的检索工具能显著提升智能体的准确性和一致性。
New Anthropic research shows AI agents may look br…
New Anthropic research shows AI agents may look brilliant at code, but in biology they can fail before the science starts.
Strong AI agents could give very different answers to the exact same biology data request, even when nothing changed in the prompt.
In one Ebola sequence task, Claude Sonnet 4 returned 106 sequences in 1 run, then 15, then 5, while the expected answer was 266.
Those missing sequences did not just make the dataset messy, they changed the scientific story built on top of it.
One bad retrieval made the outbreak look like it traced back to 1922, instead of the manually curated result pointing to early 2014.
The biology databases were too hard to use reliably through current AI tools.
The agents often understood what they were being asked, but their answers varied a lot because they had to fight through scattered databases, hidden website rules, and fragile scripts.
The key finding is that adding a repeatable retrieval tool made agents far more accurate and much more consistent.