---
title: "University of Oslo Teaches Robots to Share Brains and Evolve Faster"
subtitle: "Researchers show that soft robots trained with knowledge from peers learn faster than isolated learners, and learning from multiple teachers yields more consistent gains."
url: "https://alphasignal.ai/news/university-of-oslo-teaches-robots-to-share-brains-and-evolve-faster"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-04-14T00:00:00.000Z"
updated: "2026-08-23T23:36:54.404Z"
type: "Paper"
topics:
  - "Robotics"
  - "Training Infra"
subtopics:
  - "Vla Models"
  - "Distributed Training"
upvotes: 3547
source_url: "https://arxiv.org/abs/2604.12482"
comments: 0
truncated: true
---

# University of Oslo Teaches Robots to Share Brains and Evolve Faster

> Researchers show that soft robots trained with knowledge from peers learn faster than isolated learners, and learning from multiple teachers yields more consistent gains.

Evolving a robot's body and its controller at the same time is one of the messier problems in robotics. Shape determines what kind of movement is possible, but you can only tell if a morphology is good once you have trained a decent controller for it, and training a controller is expensive. A new paper from the University of Oslo, University of Toulouse Capitole, and the University of Trieste, [accepted at GECCO 2026](https://arxiv.org/abs/2604.12482), asks a simple question: if one robot already figured out how to move a squishy body, can others skip ahead by borrowing what it learned?

Their answer is yes, and the details are more interesting than the headline suggests.

## Why body-brain co-evolution is painful

In evolutionary robotics, the search space is tangled because body and brain depend on each other, and a promising morphology often gets discarded before its controller has a chance to catch up. The usual fix is a nested loop: an outer evolutionary process tweaks bodies, and an inner learning process trains a controller for each new body. That works, but every offspring pays the full cost of learning from scratch.

Lamarckian inheritance, where offspring receive optimized control parameters from their parents, has improved performance in prior work. The authors push further and ask why knowledge transfer should be restricted to parent-child pairs when any robot in the population might have something useful to contribute.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Social Learning Strategies for Evolved Virtual Soft Robots](https://arxiv.org/abs/2604.12482)
- [Social Learning Strategies for Evolved Virtual Soft Robots (HTML)](https://arxiv.org/html/2604.12482)
- [Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots](https://arxiv.org/abs/2201.09863)
- [Replication Data for Social Learning Strategies for Evolved Virtual Soft Robots](https://tinyurl.com/3rhzkm9t)