From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

2026-04-24

AI Summary

Existing multi-agent systems are often constrained by fixed team structures, tightly coupled coordination mechanisms, and static learning paradigms, hindering dynamic reorganization and continuous evolution. To address these limitations, this work proposes the OneManCompany (OMC) framework, which introduces an enterprise-inspired organizational layer: it encapsulates skills, tools, and configurations into abstract “talents,” orchestrates heterogeneous agents through typed organizational interfaces, and enables on-demand recruitment and dynamic reconfiguration via a talent marketplace. OMC further integrates an Explore-Execute-Review (E²R) tree search to unify planning, execution, and evaluation within a closed-loop process. Experimental results demonstrate that OMC achieves an 84.67% success rate on PRDBench, outperforming the current state-of-the-art by 15.48 percentage points, while cross-domain case studies validate its generality and adaptability.

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning. We argue that this reflects a deeper absence: a principled organisational layer that governs how a workforce of agents is assembled, governed, and improved over time, decoupled from what individual agents know. To fill this gap, we introduce \emph{OneManCompany (OMC)}, a framework that elevates multi-agent systems to the organisational level. OMC encapsulates skills, tools, and runtime configurations into portable agent identities called \emph{Talents}, orchestrated through typed organisational interfaces that abstract over heterogeneous backends. A community-driven \emph{Talent Market} enables on-demand recruitment, allowing the organisation to close capability gaps and reconfigure itself dynamically during execution. Organisational decision-making is operationalised through an \emph{Explore-Execute-Review} ($\text{E}^2$R) tree search, which unifies planning, execution, and evaluation in a single hierarchical loop: tasks are decomposed top-down into accountable units and execution outcomes are aggregated bottom-up to drive systematic review and refinement. This loop provides formal guarantees on termination and deadlock freedom while mirroring the feedback mechanisms of human enterprises. Together, these contributions transform multi-agent systems from static, pre-configured pipelines into self-organising and self-improving AI organisations capable of adapting to open-ended tasks across diverse domains. Empirical evaluation on PRDBench shows that OMC achieves an $84.67\%$ success rate, surpassing the state of the art by $15.48$ percentage points, with cross-domain case studies further demonstrating its generality.

Problem

• multi-agent systems
• organisational layer
• dynamic reconfiguration
• heterogeneous agents
• self-improving AI

Innovation

• multi-agent organisation
• Talent Market
• Explore-Execute-Review
• self-organising AI
• heterogeneous agents