Agents
3 agents available in the DeepSeek directory
agenticPARL
PARL (Parallel-Agent Reinforcement Learning) is a training paradigm that teaches models to decompose complex tasks into parallel subtasks and coordinate multiple agents simultaneously.
T
The-Swarm-Corporation 40
deepseekLanggraph-bi-agent-orchestrator
Multi-agent business intelligence orchestration system powered by GPT-5/Deepseek v3.2exp, LangGraph, and research-augmented generation.
H
Hussain0327 1
agentColab-ML-Pipeline-Agent
Agente en Colab que, dado un dataset en CSV, planifica y ejecuta un pipeline de Machine Learning de inicio a fin: análisis inicial, preprocesamiento, entrenamiento con Scikit-Learn y reporte automático con evalcards.
R
Ricardouchub 1