The Singularity Report

We introduce WebArxiv, a static-snapshot benchmark comprising 510 time-invariant tasks, each with a unique deterministic ground truth. It comes from a paper posted to arXiv on 23 September 2026. Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsing, underrepresent research-oriented environments and scholarly discovery workflows, and often depend on live sites whose changing content and structure undermine reproducibility. arXiv provides a realistic, reproducible, hierarchically structured, information-centric testbed without privacy-sensitive interactions. Its diverse, realistic scholarly tasks go beyond simple information lookup and rule following to emphasize multi-constraint paper retrieval, fine-grained content extraction, and cross-paper comparison. Evaluations of a range of foundation-model-based web agents show that WebArxiv remains challenging. Behavioral analysis reveals that agents over-rely on fixed interaction histories, causing incomplete or repetitive reasoning. We therefore equip agents with a lightweight dynamic-memory mechanism for adaptive retrieval and reasoning over relevant context. The benchmark and code are available at https://anonymous.4open.science/r/74E4423BVNW/README.md.

Why it counts

We introduce WebArxiv, a static-snapshot benchmark comprising 510 time-invariant tasks, each with a unique deterministic ground truth. The benchmark and code are available at https://anonymous.4open.science/r/74E4423BVNW/README.md.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.