AI Search Agents Exposed: They're Not Actually Searching, Just Confirming Biases
A shocking new study reveals that top AI search agents rely heavily on their existing knowledge, rather than actually researching the web, with models like GPT-5.4 and Gemini 3.1 Pro scoring high on benchmarks without even accessing the internet. This intrinsic knowledge dependence has significant implications for developers, businesses, and everyday users who rely on these models for accurate information.
Leading AI search agents like GPT-5.4 and Kimi K2.6 don't appear to do much actual research on established benchmarks. They mostly just use the web to confirm what they already learned during training. Researchers at the Harbin Institute of Technology found this using a new time-based benchmark called LiveBrowseComp, which only asks about events from the last 90 days. Once the models can't fall back on memory, performance falls apart and the existing rankings get reshuffled. The article AI search agents often confirm what they already know instead of actually researching the web appeared first on The Decoder.