從技能到人才：將異質性智能體組織為現實企業

摘要

儘管個體智能體能力已通過模組化技能與工具整合快速提升，但多智能體系統仍受制於固定團隊結構、緊耦合的協調邏輯以及會話綁定的學習模式。我們認為這反映出更深層次的缺失：一個能夠規範智能體群體如何組建、治理並持續改進的原則性組織層級，該層級應與個體智能體的具體知識解耦。為填補這一空白，我們提出OneManCompany（OMC）框架，將多智能體系統提升至組織級別。OMC將技能、工具與運行時配置封裝為可移植的智能體身份「天賦」，並通過抽象異構後端的類型化組織接口進行編排。社區驅動的天賦市場支持按需招募，使組織能在執行期間動態彌補能力缺口並重構自身。組織決策通過探索-執行-審閱（E²R）樹搜索實現操作化，將規劃、執行與評估統一於單層級循環中：任務自上而下分解為可問責單元，執行結果自下而上匯聚以驅動系統性審閱與優化。此循環不僅提供終止性與無死鎖的形式化保證，更映射了人類企業的反饋機制。這些創新共同將多智能體系統從靜態預配置管道，轉變為能夠適應跨領域開放式任務的自組織、自優化AI組織。在PRDBench上的實證評估顯示，OMC達成84.67%的成功率，較現有最佳技術提升15.48個百分點，跨領域案例研究進一步驗證了其通用性。

English

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 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 Talents, orchestrated through typed organisational interfaces that abstract over heterogeneous backends. A community-driven 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 Explore-Execute-Review (E^2R) 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.

從技能到人才：將異質性智能體組織為現實企業

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

摘要

Support