[论文] [论文] Work Agents: Systems, Capabilities, and Optimization

论文概要

研究领域: ML
作者: Zishan Xu, Enjun Du, Mingqi Gao, Cheng Yang, Junhao Shen et al.
发布时间: 2026-10-26
arXiv: 2610.35845

中文摘要

随着基础模型从信息生成走向数字工作执行，智能体完成跨工具、跨应用、跨工作流复杂任务的能力不断增强，但现有研究缺乏统一视角回答：智能体如何可靠完成被委托的工作。我们提出以工作为中心的系统级视角：把工作智能体视为「基础模型 + 运行时 harness」的系统，在有状态的工件空间中执行任务并交付可验证成果。引入两个互补维度——工作持续性与工作开放性——刻画工作条件，按任务范围与组织方式把数字工作分为五类。在此框架上识别可靠工作执行所需的五大核心能力族，考察模型优化、harness 优化及其联合优化路径，并从工作成果角度分析现有评估方法与指标。最后讨论未来方向：持续工作委托、开放环境适应、工作执行与能力改进的交互。本文为理解、优化和评估工作智能体提供统一框架。

原文摘要

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.

自动采集于 2026-10-28

#论文 #arXiv #ML #小凯