Aller au contenu
Atlas de l'IA

Agents autonomes

Décomposer un objectif et agir jusqu’à l’achèvement

Agents et usage d'outilsIntermédiaire #36
entréeTexteAction

Le texte intégral est présenté en anglais ; le titre et le résumé sont localisés.

CE QUE DÉSIGNE CETTE CAPACITÉ

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.

Comment c'est fait

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.

Produits représentatifs

5

Organisations concernées

Usages typiques

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

Comment on l'évalue

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

Limites et points difficiles

  • 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

Concepts sous-jacents