ysymyth/ReAct
ReAct
ReAct es una plantilla de flujo de trabajo de agentes y framework de prompts para modelos de lenguaje grandes (LLM). Implementa un patrón lógico que integra el razonamiento de cadena de pensamiento (chain-of-thought) con la ejecución de herramientas externas para resolver tareas complejas de múltiples pasos.
El framework utiliza una lógica entrelazada de razonamiento y actuación, forzando al modelo a documentar su proceso de pensamiento interno antes de ejecutar una acción. Este ciclo de planificación y actuación permite al sistema interactuar con APIs o bases de datos externas e inyectar datos del mundo real de vuelta en el contexto del modelo para refinar las rutas de razonamiento.
El proyecto cubre la ejecución autónoma de tareas y la orquestación de agentes combinando la integración de observación-retroalimentación con una lógica de ejecución impulsada por prompts. Esto asegura un ciclo continuo de pensamiento, actuación y observación para lograr objetivos sin intervención humana constante.
Features
- Reasoning-Action Loops - Implements a core loop that alternates internal reasoning steps with external tool execution to iteratively solve tasks.
- Agent Task Orchestrators - Orchestrates the interaction between reasoning cycles and tool use to manage stateful agent workflows.
- Agentic LLM Frameworks - Provides a framework for building agents that combine chain-of-thought reasoning with external tool execution.
- LLM Tooling Integrations - Implements connectors that allow language models to access external data and execute software tools.
- Chain of Thought Implementations - Implements a logic structure that requires the model to document its reasoning before executing an action.
- Autonomous Task Execution - Enables language models to plan and execute sequences of actions to achieve goals without human intervention.
- Chain-of-Thought Prompting - Implements a structured chain-of-thought prompting methodology to guide models through step-by-step logical reasoning.
- Interleaved Logic Execution - Utilizes a prompting pattern that alternates between internal thoughts and external tool-based actions.
- Conversation Context Management - Maintains conversation coherence by appending tool observations and reasoning traces to the interaction state.
- External Tool Integrations - Connects language models to external APIs and databases to retrieve real-time information and perform actions.
- Reasoning-Action Implementations - Implements the specific logic pattern of alternating planning and acting to solve complex multi-step tasks.
- Reasoning Task Execution - Combines chain-of-thought reasoning with tool execution to solve complex, multi-step problem sets.
- Prompt State Updates - Updates the internal model context by appending the outputs of external API calls to the conversation history.
- Prompt-Driven Execution Loops - Uses structured natural language templates to orchestrate a repeating cycle of thinking, acting, and observing.
- Prompt Feedback Loops - Injects real-world tool outputs back into the model context to correct reasoning and update the internal state.
- Prompt Chaining Frameworks - Orchestrates a sequence of prompts where reasoning steps and tool outputs inform subsequent model inputs.
- Reasoning-Action Templates - Provides a structured prompting template for guiding models through an iterative cycle of planning and observation.
- Agent Action Frameworks - Synergizing reasoning and acting in language models.
- Embodied Agents - Synergizing reasoning and acting capabilities in language models.
- Task and Motion Planning - Synergizing reasoning and acting in language models.
