MEGA Hub

Work Agents: Systems, Capabilities, and Optimization

Authors

Do you know Zishan Xu?You can claim authorship or link another user.Do you know Enjun Du?You can claim authorship or link another user.Do you know Mingqi Gao?You can claim authorship or link another user.Do you know Cheng Yang?You can claim authorship or link another user.Do you know Junhao Shen?You can claim authorship or link another user.Do you know Zirong Chen?You can claim authorship or link another user.Do you know Zhiyuan Yao?You can claim authorship or link another user.Do you know Yifu Guo?You can claim authorship or link another user.Do you know Yuquan Lu?You can claim authorship or link another user.Do you know Jinyang Huang?You can claim authorship or link another user.Do you know Zhengxi Lu?You can claim authorship or link another user.Do you know Siyi Liu?You can claim authorship or link another user.Do you know Ziyu Zheng?You can claim authorship or link another user.Do you know Yongqi Zhang?You can claim authorship or link another user.Do you know Difan Zou?You can claim authorship or link another user.Do you know Weiwen Liu?You can claim authorship or link another user.

Abstract

As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workflows. However, existing research lacks a unified perspective on how agents reliably accomplish delegated work. To address this gap, we present a work-centric, system-level perspective that views work agents as systems combining foundation models and runtime harnesses to execute tasks in stateful workspaces and deliver verifiable outcomes. We introduce two complementary dimensions, work persistence and work openness, to characterize working conditions, and classify digital work into five forms according to task scope and organization. Building on this framework, we identify five core capability families required for reliable work execution and examine approaches to model optimization, harness optimization, and their joint optimization. We further analyze existing evaluation methods and metrics from the perspective of work outcomes. Finally, we discuss future research directions, including sustained work delegation, adaptation to open environments, and the interaction between work execution and capability improvement. This paper provides a unified framework for understanding, optimizing, and evaluating work agents, supporting the development of systems capable of delivering reliable, verifiable, and practically valuable work outcomes.

Community

00