Work State-Centric AI Agents: Design, Implementation, and Management of Cognitive Work Threads
This addresses a gap in AI agent systems for better task oversight and auditing, though it appears incremental as it builds on existing concepts like ReAct.
The paper tackles the problem of dynamic management of work state information during AI task execution by proposing a work state-centric agent model with 'work notes' to record states, resulting in improved task execution efficiency and a foundation for analysis and auditing.
AI agents excel in executing predefined tasks, but the dynamic management of work state information during task execution remains an underexplored area. We propose a work state-centric AI agent model employing "work notes" to record and reflect the state throughout task execution. This paper details the model's architecture, featuring worker threads for task oversight, planner modules for task decomposition and planning, and executor modules for performing subtasks using a ReAct-inspired thought-action loop. We provide an exhaustive work state record incorporating plans and outcomes, constituting a comprehensive work journal. Our results show that this model not only improves task execution efficiency but also lays a solid foundation for subsequent task analysis and auditing.