paper-with-me

Papers

OpenComputer: Verifiable Software Worlds for Computer-Use Agents

2026-05-19 · Jinbiao Wei, Qianran Ma, Yilun Zhao, Xiao Zhou, Kangqi Ni, Guo Gan, Arman Cohan arxiv

We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection endpoints over real applications, (2) a self-evolving verification layer that improves verifier reliability using execution-grounded feedback, (3) a task-generation pipeline that synthesizes realistic and machine-checkable desktop tasks, and (4) an evaluation harness that records full trajectories and computes auditable partial-credit rewards. In its current form, OpenComputer covers 33 desktop applications and 1,000 finalized tasks spanning browsers, office tools, creative software, development environments, file managers, and communication applications. Experiments show that OpenComputer's hard-coded verifiers align more closely with human adjudication than LLM-as-judge evaluation, especially when success depends on fine-grained application state. Frontier agents struggle with end-to-end completion despite partial progress, and open-source models exhibit sharp drops from their OSWorld-Verified scores, exposing a persistent gap in robust computer automation.

📄 PDF Abstract BibTeX arXiv:2605.19769

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Tactile: Giving Computer-Using Agents Hands and Feet

2026-07-16 · Yong Liu, Zhenyi Zhong, Zhanpeng Shi arxiv

Computer-use agents are becoming capable software operators, but their interface to desktop applications is still often a brittle motor layer: they look at screenshots, predict coordinates, click, and hope that the visib…

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

2026-05-25 · Bowen Wang, Dunjie Lu, Junli Wang, Tianyi Bai 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the sca…

Reinforcement Learning

MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps

2026-08-18 · Sujin Chen, Lijun Li, Tianyi Du, Jing Shao arxiv

LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. However, because these agents routinely process untrusted environmental cont…

YeasierAgent: Agentic Social Sandbox as a Canvas for Intent-Driven Creation of Platform-Agnostic Symbiotic Agent-Native Applications

2026-06-11 · Jory He arxiv

This paper introduces YeasierAgent, an application-building paradigm based on symbiotic agents, narrative worlds, and scene-aware interaction. It challenges the conventional device-coupled model of software by redefining…

Revisiting DAgger in the Era of LLM-Agents

2026-05-13 · Changhao Li, Rushi Qiang, Jiawei Huang, Chenxiao Gao 외 arxiv

Long-horizon LM agents learn from multi-turn interaction, where a single early mistake can alter the subsequent state distribution and derail the whole trajectory. Existing recipes fall short in complementary ways: super…

Reinforcement Learning