Paper page - Work Agents: Systems, Capabilities, and Optimization

Source: https://huggingface.co/papers/2610.35845 Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

The paper proposes a unified framework for work agents that integrates foundation models with runtime harnesses to execute complex digital tasks reliably, introducing dimensions of persistence and openness alongside capability families and evaluation metrics.

Asfoundation modelsevolve 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 viewswork agentsas systems combiningfoundation modelsandruntime harnessesto execute tasks instateful workspacesand deliver verifiable outcomes. We introduce two complementary dimensions,work persistenceandwork 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 tomodel optimization,harness optimization, and theirjoint optimization. We further analyze existing evaluation methods and metrics from the perspective ofwork 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 evaluatingwork agents, supporting the development of systems capable of delivering reliable, verifiable, and practically valuablework outcomes.

View arXiv pageView PDFProject pageGitHub56Add to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.35845 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.35845 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.35845 in a Space README.md to link it from this page.

Collections including this paper2