ACL Findings2025
AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant
Chengyou Jia, Minnan Luo, Zhuohang Dang, Qiushi Sun, Fangzhi Xu, Junlin Hu, Tianbao Xie, Zhiyong Wu
Abstract
Digital agents capable of automating complex computer tasks have attracted considerable attention due to their immense potential to enhance human-computer interaction. However, existing agent methods exhibit deficiencies in their generalization and specialization capabilities, especially in handling open-ended computer tasks in real-world environments. Inspired by the rich functionality of the App store, we present AgentStore, a scalable platform designed to dynamically integrate heterogeneous agents for automating computer tasks. AgentStore empowers users to integrate third-party agents, allowing the system to continuously enrich its capabilities and adapt to rapidly evolving operating systems. Additionally, we propose a novel core MetaAgent with the AgentToken strategy to efficiently manage diverse agents and utilize their specialized and generalist abilities for both domain-specific and system-wide tasks. Extensive experiments on three challenging benchmarks demonstrate that AgentStore surpasses the limitations of previous systems with narrow capabilities, particularly achieving a significant improvement from 11.21% to 23.85% on the OSWorld benchmark, more than doubling the previous results. Comprehensive quantitative and qualitative results further demonstrate AgentStore's ability to enhance agent systems in both generalization and specialization, underscoring its potential for developing the specialized generalist computer assistant. All our codes will be made publicly available in https://chengyou-jia.github.io/AgentStore-Home.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
7 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents cites OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
- OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis cites WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
Cited by top-tier papers7
- OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisQiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin et al.ACL 2025 · 114 citations
- GUI-Actor: Coordinate-Free Visual Grounding for GUI AgentsQianhui Wu, Kanzhi Cheng, Rui Yang, Chaoyun Zhang et al.NeurIPS 2025 · 98 citations
- TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI AgentsBofei Zhang, Zirui Shang, Zhi Gao, Wang Zhang et al.AAAI 2026 · 26 citations
- OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using AgentsBowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu et al.ACL 2026 · 15 citations
- OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic WorkflowsQiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie et al.ACL 2026 · 14 citations
Builds on16
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- PaLM-E: An Embodied Multimodal Language ModelDanny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch et al.ICML 2023 · 2,601 citations
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin et al.NeurIPS 2023 · 1,975 citations
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
- WebShop: Towards Scalable Real-World Web Interaction with Grounded Language AgentsShunyu Yao, Howard Chen, John Yang, Karthik NarasimhanNeurIPS 2022 · 1,477 citations
Related papers
- Agent S: An Open Agentic Framework that Uses Computers Like a HumanSaaket Agashe, Jiuzhou Han, Shuyu Gan, Jiachen Yang et al.ICLR 2025 · 2 citations
- Computer Agent Arena: Toward Human-Centric Evaluation and Analysis of Computer-Use AgentsBowen Wang, Xinyuan Wang, Jiaqi Deng, Tianbao Xie et al.ICLR 2026
- CoAct-1: Computer-using Multi-agent System with Coding ActionsLinxin Song, Yutong Dai, Viraj Prabhu, Jieyu Zhang et al.ICLR 2026 · 32 citations
- AgentStudio: A Toolkit for Building General Virtual AgentsLongtao Zheng, Zhiyuan Huang, Zhenghai Xue, Xinrun Wang et al.ICLR 2025
- WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application EnvironmentsJinchao Li, Yunxin Li, Chenrui Zhao, Zhenran Xu et al.ACL Findings 2026
