LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-05-27 with 13 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | HuiMing Fan et al. |
| Year | 2026 |
| HF Upvotes | 13 |
| arXiv | 2605.28721 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
Are LLM-based search agents genuinely searching, or using the web to verify what they already know? We study this question on BrowseComp with three diagnostics. Our analysis reveals Intrinsic Knowledge Dependence (IKD): even with tool access, agents often rely on intrinsic knowledge -- information encoded in the model before retrieval -- rather than on external evidence. Agents answer up to 44.5% of BrowseComp questions without tools, generate more than half of their search queries from internally produced hypotheses rather than retrieved leads, and perform worse than closed-book baselines when answer-supporting evidence is removed. These results suggest that static search benchmarks can reward memory-backed verification rather than evidence-driven discovery, conflating what agents already know with what they can find. We then introduce LiveBrowseComp, a deep-search benchmark designed to evaluate agents beyond intrinsic coverage. It contains 335 human-authored questions whose answers depend on facts published within the 90 days preceding benchmark construction, drawn from six updated sources and filtered to exclude globally salient events. On LiveBrowseComp, all evaluated agents fall below 2% closed-book accuracy, search-augmented scores drop by 25-40 points relative to BrowseComp, and prior model rankings no longer reliably predict performance. LiveBrowseComp is available at https://huggingface.co/datasets/Forival/LiveBrowseComp.
Engineering Breakdown
The Problem
Are LLM-based search agents genuinely searching, or using the web to verify what they already know?
The Approach
We study this question on BrowseComp with three diagnostics.
Key Results
LiveBrowseComp is available at https://huggingface.co/datasets/Forival/LiveBrowseComp.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Livebrowsecomp
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::