arXiv:2601. 04126v3 Announce Type: replace-cross Abstract: GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants.
arXiv:2603. 26648v3 Announce Type: replace-cross Abstract: Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited.
arXiv:2605. 25160v2 Announce Type: replace Abstract: GUI agents powered by large language models are advancing rapidly, creating urgent needs for evaluation and training based on realistic environments.
arXiv:2608.21898v1 Announce Type: new Abstract: Web agents promise to automate complex digital workflows, but their training remains limited by synthetic environments that look plausible while hiding...
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.
The paper introduces Test-Time Environment Decomposition (TTED), a label‑free learning method that allows large language model agents to break down complex web environment observations into simpler sub‑modules during inference. By learning from experience within these sub‑environments, agents can compose the gained knowledge to improve performance in the full environment. Experiments on synthetic and realistic benchmarks show that this approach enhances compositional generalization and boosts real‑world web automation tasks.
The paper introduces OdoBot, a web‑agent architecture that reduces token usage by modeling application behavior from successful task demonstrations. Compared to two state‑of‑the‑art agents, OdoBot uses 44% and 80% fewer tokens on 45 tasks in the Canvas Learning Management System, and it also achieves a higher task success rate than WebVoyager.
arXiv:2506. 01952v2 Announce Type: replace-cross Abstract: Powered by large language models (LLMs), web browsing agents operate graphical user interfaces in a human-like manner, offering a transparent and general framework for automating web-based tasks.
The paper introduces KNOWS, a benchmark for evaluating web agents that act as assistants by retrieving, synthesizing, and presenting information across complex, multi-step browser tasks. It outlines a task design rubric, evaluation protocol combining deterministic checks with LLM judgments, and reports that current agents achieve only modest success, with the best performing agent succeeding on less than 3% of tasks. The study highlights significant gaps in agents’ tool use, visual understanding, and long‑horizon reasoning.
Wuying-Browser-Agent is a unified framework designed to improve long-horizon browser agents by aligning execution, supervision, optimization, and evaluation. It introduces a structured browser harness, reflection and UI-specialized Curriculum SFT (RUIC‑SFT) for recovery and complex UI interactions, and Divergence‑Aware Online GRPO (DAO‑GRPO) for better credit assignment. The framework is evaluated on BrowserBench—a bilingual real‑web benchmark of 350 tasks—and achieves state‑of‑the‑art results on multiple browser‑use benchmarks, while also transferring well to other agentic tasks.
arXiv:2604.13318v2 Announce Type: replace Abstract: Autonomous web agents powered by large language models (LLMs) remain brittle on long-horizon browser workflows. A key bottleneck is a grounding gap...
arXiv:2606. 29705v1 Announce Type: new Abstract: Data, as the fundamental substrate of modern intelligence, has greatly driven the development of current foundation models.