# Meta AI introduces MIRA architecture for long-horizon research agents

Meta AI researchers introduced MIRA, a dual-component agent architecture that decouples meta-reasoning from execution to improve decision-making in long-horizon research tasks.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/cfe4121651ba440497b3c965.html

Content language: en
Localization state: sameLanguage

Source: DAIR.AI · Published 10/6/2026, 07:57:26

In an [arXiv paper](https://arxiv.org/abs/2610.02525), Meta AI researchers proposed MIRA, an architecture designed to help research agents decide what to investigate next during long-horizon tasks. To overcome the difficulty of learning from sparse decisions in long execution traces, MIRA splits the agent into an outer meta-reasoner that reads a persistent research record to issue work orders, and a fresh executor that carries out each order.

Because decisions occur exclusively at work-order boundaries, the researchers train a critic at those points to forecast remaining return, followed by a unified actor-critic model (MIRA-AC) that assesses partial progress and chooses the next task. The structural separation improves theorem proving and open-ended architecture research without training, while MIRA-AC trained on the model's proxy signals improves gold scores across four autoresearch environments.

Tags: Meta AI, MIRA, AI Agents, Reinforcement Learning

[View original post](https://x.com/dair_ai/status/2107482016342233309)