AIM Labs

Research

EN

Research

Systems that plan,
adapt and act.

Notes from AIM Labs on world models, multi-agent planning and robotics.

Latest

Research notes and results.

Competition · July 2026

First place in the League of Robot Runners 2026 combined evaluation.

Three AIM Labs team members built a high-throughput multi-agent planning system. It completed 310,466 tasks and achieved the highest combined score of 10.628 after 87 competition submissions.

Read the research

Contact

Bring us the
hard problem.