arXiv:2607. 00007v2 Announce Type: replace-cross Abstract: Large language model (LLM)-based web agents automate web navigation and data collection.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2607. 00007v1 Announce Type: cross Abstract: Large language model (LLM)-based web agents reduce manual scripting for web data collection, yet on live websites, they often miss relevant pages, return incomplete multimodal outputs, or return media URLs that are not directly downloadable.
Web agents that act from rendered pixels avoid the fragility and heavy token cost of reading a page's HTML or accessibility tree, but training them depends on large amounts of high-quality interaction...
WebArxiv is a reproducible benchmark designed to evaluate multimodal web agents on arXiv-related tasks. It consists of 510 static, time‑invariant tasks that require multi‑constraint paper retrieval, fine‑grained content extraction, and cross‑paper comparison, each with a deterministic ground truth. The benchmark highlights challenges for foundation‑model agents, such as over‑reliance on fixed interaction histories, and introduces a lightweight dynamic‑memory mechanism to improve adaptive retrieval and reasoning.
The paper investigates how to improve large language model (LLM) based autonomous web agents by filtering irrelevant webpage content. The authors reproduce baseline models on the WebArena benchmark and identify failure modes caused by raw HTML input. They propose DeBERTa‑ and T5‑based retrieval models that rank HTML elements by relevance, fine‑tuned on Mind2Web data, and demonstrate that the DeBERTa model raises the LLaMA‑2‑70B agent’s success rate from 1.97% to 2.96%. Additionally, a zero‑shot ColBERT retriever achieves recall of 0.52 on Mind2Web and 0.47 on WebArena.
arXiv:2606. 02031v1 Announce Type: cross Abstract: Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites.
Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories.