AI 搜索代理往往只是确认其已知信息,而非真正研究网络
阅读原文· the-decoder.com哈尔滨工业大学研究人员发现,包括 GPT-5.4 和 Kimi K2.6 在内的领先 AI 搜索代理,在已有的基准测试上并未进行太多真正的网络研究。它们主要利用网络来确认其在训练阶段已学到的知识。研究团队使用名为 LiveBrowseComp 的新基准测试得出了该结论,此测试仅涉及过去 90 天内的事件。当模型无法依赖既有记忆时,其表现显著下降,现有的性能排名也随之改变。
AI search agents often confirm what they already know instead of actually researching the web
A new study suggests that leading AI search agents don't actually research on established benchmarks; they mostly use the web to confirm answers they already have. Once models have to go beyond their existing knowledge, search performance falls apart.
Frontier models like GPT-5.4, Gemini 3.1 Pro, Claude Sonnet 4.6, DeepSeek-V4-Pro, and Kimi-K2.6 keep posting higher scores on BrowseComp. The benchmark asks agents complex questions that can only be answered through multi-step browsing and piecing together information from different web sources.
Researchers from the Harbin Institute of Technology and Xiaohongshu have now shown in a study that these results say less about the agents' research skills than assumed. The authors call it "intrinsic knowledge dependence" (IKD), a reliance on internal knowledge the models absorbed during training.