Work State-Centric AI Agents: Design, Implementation, and Management of Cognitive Work Threads
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.
Code (0)
등록된 구현이 없습니다.
Tasks
AI AgentManagementSimilar Papers 제목 키워드 기반
Interpretable end-to-end Neurosymbolic Reinforcement Learning agents
Deep reinforcement learning (RL) agents rely on shortcut learning, preventing them from generalizing to slightly different environments. To address this problem, symbolic method, that use object-centric states, have been…
Atari GamesDeep Reinforcement LearningObjectreinforcement-learning+2Formally Specifying the High-Level Behavior of LLM-Based Agents
Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, th…
Question AnsweringRSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capability gaps, designing and validating training-data strategies, and le…
Question AnsweringImplementation with Uncertain Evidence
We study a full implementation problem where a socially desirable outcome depends on a state of the world which is unknown to the designer but (commonly) known to a set of agents. The designer may ask the agents to prese…
SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecasts
Self-driving vehicles rely on multimodal motion forecasts to effectively interact with their environment and plan safe maneuvers. We introduce SceneMotion, an attention-based model for forecasting scene-wide motion modes…