# Opus 5.5 and GPT-6 agents design robots; failure videos fix most flaws

MIT researchers had four coding agents design small brick-style robots and then built every design that worked in simulation. Most held up on real obstacle courses, and watching videos of their failures let the agents fix most of the rest.

- Category: Robotics
- Readiness level: II (Benchmarked) on Science Underway's four-step scale, as proposed
- Published: 2026-11-19
- Editor: Stefan Perdal
- URL: https://scienceunderway.com/articles/opus-5-5-and-gpt-6-agents-design-robots-failure-videos-fix-most-flaws

## The study

RoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop (preprint, not peer reviewed). arXiv 2611.23855. https://arxiv.org/abs/2611.23855

## At a glance

- What it shows: AI coding agents can design small robots from a box of real parts that cross simple obstacles in the real world, not only in a computer model. When an agent saw video of its robot failing, it redesigned the robot, and most of the new designs worked.
- What it does not show: It does not show that AI can engineer real machines in general. These were small, slow, toy-scale robots with no sensors, on fixed courses, and each agent ran each task only once.
- Why it matters: Many AI design tools are judged only in simulation. This study shows that a simulator never checked against reality can be badly wrong. Real tests have to be part of the loop.

## What the study shows

The researchers built a test in which coding agents design a robot and its motor program. Coding agents are AI models that write and run code on their own. The robots use standard brick-style parts, motors and, if needed, one custom 3D-printed part. They must cross ten obstacles, such as a ramp, a wall and a rope, each at three levels of difficulty. The work is a preprint and has not been peer reviewed.

Four agents were tested: Opus 5.5 and Sonnet 5.5 in Claude Code, and GPT-6 Astra and GPT-6.1 Sol in Codex. With a printed part allowed, they passed 98% of the easiest tasks in simulation, 70% at level 2 and 48% at level 3. Automated search over the same parts, with the same budget of 30 simulations, passed none. A single model call without a simulator passed almost nothing.

Simulation alone misled badly at first. With a simulator built from public part data, none of 15 passing designs crossed the real course. Tyres slipped, joints pulled apart and gears jumped out of mesh. One agent then tuned the simulator using bench tests and videos of real runs. After that, about two thirds of simulated passes crossed for real.

The researchers then closed the loop. Each real failure at levels 1 and 2 went back to the agent that designed it, as video. The agent could correct its own copy of the simulator and then redesign. This cut real failures from 18 to 5, and the share of simulated passes that crossed for real rose from 73% to 93%.

Building one robot for all ten easy obstacles was much harder. The best single robot crossed six of ten on the real courses, because the obstacles make conflicting demands. The bumps need clearance, the bridge a narrow track, the rope a light frame hung from above.

The authors built 135 robots by hand, from about 13,000 pieces, in an estimated 240 hours. They report 16,427 simulations of 12,774 distinct robots.

## Our reading

In our reading, the strongest result is the failure of the first simulator. Not one of 15 designs that passed in a standard physics model worked in the real world. That is a useful warning for anyone who trusts a simulated score as proof that an AI-designed machine works. A model of the parts is not a model of how a small, loosely built robot fails.

The hardware loop is the practical idea. An agent watches its robot stall at a step, notes the cause, and tries again. On the bumps course, Opus 5.5 saw its spoked wheels spinning against a ridge, lowered a friction value in its simulator, and switched to a different wheel design that crossed. This is roughly how an engineer works with a prototype. The authors are careful that this measures recovery on the same course, not success on new tasks.

We rate the work at level II, Benchmarked, on our four-level readiness scale. It sets out a new benchmark with results for four agents and several baselines. Code and data are promised under open licences, but the paper does not confirm they are public yet.

The rest of the article (what it means, limits, what to watch) is free for members: https://scienceunderway.com/articles/opus-5-5-and-gpt-6-agents-design-robots-failure-videos-fix-most-flaws

## How this was made

An AI model read the study and wrote this article in the structure Science Underway uses. An editor reviewed it and approved it for publication. Check the original study before you rely on the details.

---
Source: Science Underway, https://scienceunderway.com/. Please link to the article when you cite it.
