GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Kaiyuan Chen, Shuangyu Xie, Letian Fu, Justin Yu, William Pacini, Sandeep Bajamahal, Hudson Kim, Jaimyn Drake, Daehwa Kim, Haoru Xue, Jonathan Francis, Christian Juette, Peter Schaldenbrand, Muhammet Yunus Seker, Ruwan Wickramarachchi, Uksang Yoo, Guanzhi Wang, Adithyavairavan Murali, Balakumar Sundaralingam, S. Shankar Sastry, Spencer Huang, Yuke Zhu, Linxi 'Jim' Fan, Ken Goldberg
• Venue: arXiv: cs.RO
• Published: 2026-07-06
• Collected: 2026-07-07
• URL: http://arxiv.org/abs/2607.05369v1
• PDF: https://arxiv.org/pdf/2607.05369v1
• DOI: UNKNOWN

Plain-Language Brief

The research presents a new coding system called Graph-as-Policy (GaP) for robots to work reliably in commercial and industrial applications. GaP combines interpretable robot programming with the adaptability of model-free policies, particularly focusing on Variational Automation tasks where objects have varying geometries and positions. The system generates directed computation graphs from a Modular Open Robot Skill Library (MORSL) and simulates task instances to improve success rates and throughput.

What the Document Says

• The research introduces Graph-as-Policy (GaP), a multi-agent coding harness.
• GaP generates directed computation graphs from MORSL.
• The system creates an internal simulation environment to rehearse task instances.
• GaP aims to improve success rates and throughput for Variational Automation tasks.
• The research evaluates GaP on 8 new open VA task benchmarks, both in-simulation and real-world.
• Results suggest that GaP significantly outperforms baselines.

Key Concepts Mentioned

• Graph-as-Policy (GaP)
• Variational Automation
• Modular Open Robot Skill Library (MORSL)
• Simulation
• Success rates
• Throughput

Claims Made by the Document

• GaP can improve success rates and throughput for Variational Automation tasks.
• GaP significantly outperforms baselines.

Evidence Used

• Evaluation results with 8 new open VA task benchmarks.

Methods / Approach

• Generating directed computation graphs from MORSL
• Creating an internal simulation environment

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

For robots to work reliably in commercial and industrial applications, can recent advances in agentic coding systems combine interpretable robot programming with the open-world adaptability of model-free policies? We focus on 'Variational Automation' (VA), a class of tasks that have larger variations in object geometry and pose than fixed automation. Model-free policies often struggle to close the reliability gap for VA tasks, which must be executed persistently and reliably in commercial and industrial applications. Motivated by prior work on Task and Motion Planning (TAMP) and the Robot Operating System (ROS), we introduce Graph-as-Policy (GaP), a multi-agent coding harness that generates directed computation graphs with perception, planning, and control nodes from a Modular Open Robot Skill Library (MORSL). GaP then generates an internal simulation environment to rehearse task instances with different graphs in parallel to iteratively refine the graph structure and parameters to improve success rates and throughput. Evaluation with 8 new open VA task benchmarks, 4 in-simulation and 4 in real-world, suggests that GaP can achieve success rates that significantly outperform baselines. Details, code, and data can be found online: https://graph-robots.github.io/gap