Work Agents: Systems, Capabilities, and Optimization
Paper · https://arxiv.org/abs/2610.35845
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.
First seen by Oriel on .
AI summary
This paper presents a system-level framework for understanding, optimizing, and evaluating agents that execute delegated work across tools, applications, and workflows.
- It defines work agents as foundation models combined with runtime harnesses that operate in stateful workspaces and produce verifiable outcomes.
- Work persistence and work openness characterize working conditions, while five forms classify digital work by task scope and organization.
- The framework identifies five capability families and examines model, harness, and joint optimization approaches.
- It analyzes work-outcome evaluation methods and highlights sustained delegation, open-environment adaptation, and links between execution and capability improvement as research directions.
#ai agents #foundation models #agent evaluation #model optimization
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Hugging Face Papers: 115, latest observation ; +24 over observed period since
Comments
Comment count reported by the source.
- Hugging Face Papers: 2, latest observation ; +1 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Papers | 2610.35845 | https://arxiv.org/abs/2610.35845 Read discussion |