# French lab releases benchmark for long-horizon robot agents

> MAGMA-Bench evaluates agents in simulated multi-robot tasks with changing goals and execution failures.

- Canonical URL: https://newsverum.com/en/news/french-lab-publishes-benchmark-for-long-horizon-robot-agents
- Publisher: Newsverum
- Section: Technology
- Country: France
- Published: 2026-10-12T23:33:38+00:00
- Updated: 2026-10-12T23:33:38+00:00
- Event / data period: 2026-10-09
- Other editions: [Türkçe](https://newsverum.com/tr/news/french-lab-publishes-benchmark-for-long-horizon-robot-agents.md), [العربية](https://newsverum.com/ar/news/french-lab-publishes-benchmark-for-long-horizon-robot-agents.md), [Français](https://newsverum.com/fr/news/french-lab-publishes-benchmark-for-long-horizon-robot-agents.md), [Español](https://newsverum.com/es/news/french-lab-publishes-benchmark-for-long-horizon-robot-agents.md), [Deutsch](https://newsverum.com/de/news/french-lab-publishes-benchmark-for-long-horizon-robot-agents.md), [Português](https://newsverum.com/pt/news/french-lab-publishes-benchmark-for-long-horizon-robot-agents.md)

Researchers from LAAS-CNRS and French company Siléane introduced MAGMA-Bench in a preprint dated 9 October. The benchmark evaluates persistent reasoning in long robotic tasks. It includes 12 scenario families with one to three robots, mission changes, interruptions, partial observations and simulated execution failures.

The evaluation contains 1,254 episodes. The authors say even the strongest models they tested fail on a substantial share of clean episodes, with success rates falling further under perturbations. A shared subset of 215 episodes was used to compare frontier models. Because the benchmark separates high-level decisions from perception and low-level control and relies on simulation, the results do not establish the performance of deployed robots.

## Data

### Study scope

Simulated episodes across 12 scenario families; not real-robot deployment

Methodology: Count reported by the paper for its experimental scope; not a national statistic or field result.

| Indicator | Experimental scope count | Preprint publication date |
|---|---|---|
| MAGMA-Bench evaluation episodes | 1254 | 2026-10-09 |

Sources: <https://arxiv.org/pdf/2610.13534> · Download data: [JSON](https://newsverum.com/api/v1/articles/french-lab-publishes-benchmark-for-long-horizon-robot-agents/data/study-experimental-scope?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/french-lab-publishes-benchmark-for-long-horizon-robot-agents/data/study-experimental-scope?lang=en&format=csv)

## Sources

- [arXiv preprint by LAAS-CNRS and Siléane researchers](<https://arxiv.org/pdf/2610.13534>) (Source checked: 2026-10-13; Published: 2026-10-09)

---

Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)