Skip to content
AI News HubLIVE
Original source2 min read

It Takes Two to Tangram: Multi-Agent Object Centric Reinforcement Learning for Assembly

Summary

This paper presents an object-centric reinforcement learning framework that treats each part as an agent and learns a shared policy for geometric assembly. Using a graph neural network to encode parts, target poses, and spatial relationships, combined with per-agent PPO and a centralized graph critic, the method achieves concurrent assembly in simulation on planar Tangram tasks and transfers to sequential execution on a real robot.

SourcearXiv RoboticsAuthor: Paul Knau{\ss}t, Kay Pompetzki, Nico Bohlinger, Niklas Funk, Cristiana de Farias, Rolf Findeisen, Jan Peters
It Takes Two to Tangram: Multi-Agent Object Centric Reinforcement Learning for Assembly
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 6 Nov 2026]

Title:It Takes Two to Tangram: Multi-Agent Object Centric Reinforcement Learning for Assembly

View a PDF of the paper titled It Takes Two to Tangram: Multi-Agent Object Centric Reinforcement Learning for Assembly, by Paul Knau{\ss}t and 5 other authors

View PDF HTML (experimental)

Abstract:Geometric assembly requires fine spatiotemporal coordination to place parts without causing collisions or deadlocks under tight clearances. To address this, we present an object-centric reinforcement learning framework that treats each part as an agent and learns a shared policy for continuous assembly control. A graph neural network represents the pieces, their target poses, and their spatial relationships, and predicts translational and angular velocities for each component. Per-agent proximal policy optimization with a centralized graph critic directly learns motion and temporal coordination within a single feedback policy. We study this formulation through planar Tangram assembly, where pieces must slide and rotate into a given configuration while remaining on the assembly surface. Procedural generation of target configurations and randomized initial arrangements support training and evaluation across diverse assembly problems. Our experiments isolate the roles of relational structure and multi-agent optimization, and compare learned control with sampling-based planning. We demonstrate concurrent assembly in simulation and transfer the policy to sequential execution on a real robot, as our object-centric formulation decouples learned assembly coordination from low-level physical control. Project page: this https URL

Comments: This work has been submitted to the IEEE for possible publication

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2611.08814 [cs.RO]

(or arXiv:2611.08814v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.08814

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Cristiana Miranda De Farias [view email] [v1] Fri, 6 Nov 2026 00:11:49 UTC (1,907 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled It Takes Two to Tangram: Multi-Agent Object Centric Reinforcement Learning for Assembly, by Paul Knau{\ss}t and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Object-centric multi-agent RL framework models each part as an agent with a shared control policy.
  • Graph neural network encodes part states, target poses, and spatial relations to predict translational and angular velocities.
  • Validated on planar Tangram assembly with procedural generation and randomized initial arrangements.
  • Demonstrates concurrent assembly in simulation and transfers to sequential execution on a real robot.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

It Takes Two to Tangram: Multi-Agent Object Centric Reinforcement Learning for Assembly | AI News Hub