ComponentBench is a new benchmark that evaluates computer‑use agents at the component level on modern web UIs. It contains 97 canonical UI components and 2,910 programmatically verified tasks, along with cleaned human reference trajectories for measuring task success and interaction efficiency. The benchmark also offers a scalable pipeline for auditing structural difficulty and synthesizing failure analyses across tasks and component families.
By Tianchen Guan, Xinlei Lin, Royce Cheng-Yue, Xiangjun Wang, Shuyan Zhou
arXiv:2607. 17050v1 Announce Type: cross Abstract: GUI agents must reason about how actions transform interface states, but end-to-end success rates entangle this ability with perception, grounding, planning, and recovery.
By Yaohan Yang, Minglei Shi, Borui Zhang, Jie Zhou, Jiwen Lu
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.
By Alexander Gill, Md Farhan Ishmam, Xuyen Nguyen, Neha Bhat, Parker Henry DeYoung, Fateme Hashemi Chaleshtori, Nathan Stringham, Kenneth Marino, Ana Marasovi\'c
AnyAct introduces a universal action layer that consolidates diverse tool capabilities into a self‑evolving action space for AI agents operating in open‑world environments. It tackles the scale dilemma, tool non‑stationarity, and heterogeneous feedback by using hierarchical progressive retrieval and test‑time reliability evolution, while a heterogeneous observation grounding module unifies multi‑modal feedback. Evaluations on LiveMCPBench and the newly created OSMCP benchmark show state‑of‑the‑art performance, with significant gains in task success rate and reduced execution steps, especially for models with limited native capabilities.
By Lingrui Xu, Yangqin Jiang, Jiachang Zhang, Xubin Ren, Chao Huang
ToolRobustBench is a stage-wise diagnostic benchmark designed to evaluate and diagnose failures in tool‑calling agents, which are large language models that select tools, provide structured arguments, and interpret tool feedback. The benchmark aligns four perturbation families—tool‑interface, user‑intent, tool‑output/observation, and runtime‑environment—with the tool‑use pipeline, attributing failures to specific stages such as tool selection, schema grounding, argument binding, and feedback handling. Experiments across 15,456 instances, 7 models, and 16 local tools reveal that while overall performance is high, robustness degrades significantly, especially under tool‑output/observation perturbations, and mixed‑family perturbations produce non‑additive failure patterns.
By YiShan Zheng, Yuan Wu, Yi Chang
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
By Pengyu Zhu, Lijun Li, Yaxing Lyu, Qianxin Luo, Jingyi Yang, Yi Liu, Tingfeng Hui, Xinyu Yuan, Li Sun, Sen Su, Jing Shao
arXiv:2606. 17546v1 Announce Type: new Abstract: Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop.
By Congjie Zheng, Chuanyi Xue, Bin Liang, Jun Yang, Changshui Zhang
arXiv:2609.06059v1 Announce Type: new
Abstract: As large language models evolve from question-answering systems into general-purpose agents, evaluation must move beyond static answer correctness to a...
By Yu Liu, Zhilin Liu, Zhiwei Yang, Shaojie Zhang, Zheyuan Deng, Tingwei Huang, Zhenbo Luo, Lei Jiang, Yanbing Liu, Pei Fu
arXiv:2608. 06474v1 Announce Type: new Abstract: Large language models increasingly generate complete websites from natural-language descriptions, and reinforcement learning has become a central approach to closing their remaining functional gap.
By Boshui Chen, Huiping Liu, Shaolei Zhang
arXiv:2606. 16262v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as UX judges that inspect interfaces, diagnose usability problems, and propose repairs.
By Wenjie Wang, Yue Huang, Zipeng Ling, Han Bao, Hang hua, Xiaonan Luo, Yu Jiang, Shiyi Du, Yuexing Hao, Xiaomin Li, Yuchen Ma, Dianzhuo Wang, Yanfang Ye, Xiangliang Zhang
arXiv:2608. 07925v1 Announce Type: new Abstract: EDA scripting with tool-specific, often undocumented APIs remains a long-tail bottleneck that existing LLMs fail to address.
By Yang Liu, Shiwei Hou, Xiyuan Chen, Yu Wang, Sen Yuan, Qirui Gan, Shao You, Feifan Chen, Wencheng Li, Shuyang Hu, Yongzhou Liu, Emma Xia, Xiaojing Lu, Hao Wang, Fan Xu, Yanfeng Li
arXiv:2608. 03689v1 Announce Type: new Abstract: Large language models are increasingly capable of synthesizing executable frontend projects, yet existing benchmarks still treat web generation as a static evaluation problem.
By Yiyao Wang, Zhen Wen, Yinghao Tang, Yixiao Fu, Lin Yuan, Xiaolau Zhang, Jun Zhou, Wei Chen