Saltar al contenido
Atlas de IA

Agentes autónomos

Descomponer un objetivo y actuar hasta completarlo

Agentes y uso de herramientasIntermedio #36
entradaTextoAcción

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ SIGNIFICA ESTA CAPACIDAD

Takes a higher-level goal — fix this issue — and outputs a sequence of actions, adjusting the next step from feedback along the way. Unlike tool use it orchestrates many calls into a plan, deciding the order and when to stop; unlike a computer-use agent it works mainly through code and APIs rather than a screen interface.

Cómo se consigue técnicamente

The typical structure is a think–act–observe loop: the model plans a step, calls a tool or runs code, reads the result and revises the plan, repeating until it judges the task done. Capability comes from three things stacked together: a long-context language model, immediate feedback from an executable environment (compilation, tests, errors), and outer controls for safety and budget such as sandboxes, step limits and human checkpoints.

Productos representativos

5

Organizaciones relacionadas

Usos típicos

  • Fixing defects and submitting patches
  • Orchestrating and running data pipelines
  • Researching and assembling a report
  • Repetitive operations and scripted tasks

Cómo se evalúa

Task completion rate
Share of problems solved end to end, as in SWE-bench-style evaluation
Steps and cost
Calls and compute spent to solve the task
Human takeover rate
Share requiring a human to step in mid-task

Límites y dificultades

  • On long tasks errors accumulate, and after drifting off course the agent rarely recovers on its own
  • It can declare success without verifying: the task is announced as done while the check never ran
  • It lacks a reliable internal brake for high-risk actions such as deleting, deploying or paying, so external guardrails are needed

Conceptos detrás