GaP：面向变异性自动化任务的多智能体图即策略自学习框架
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
GaP 是一个多智能体编码框架，可从模块化开放机器人技能库（MORSL）生成含感知、规划与控制节点的有向计算图，并构建内部仿真环境并行排练不同图以迭代优化结构与参数。在 8 个新开放变异性自动化（VA）基准（4 个仿真、4 个真实世界）上，GaP 的成功率显著优于基线。
Authors: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, Yuke Zhu, Linxi "Jim" Fan, Spencer Huang, Ken Goldberg
Abstract:For robots to work reliably in commercial and industrial applications, recent advances in agentic coding systems have potential to 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 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: this https URL
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.05369 [cs.RO] |
| (or arXiv:2607.05369v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2607.05369 arXiv-issued DOI via DataCite |
Submission history
From: Jaimyn Drake [view email]
[v1]
Mon, 6 Jul 2026 17:47:31 UTC (6,853 KB)
[v2]
Fri, 23 Oct 2026 17:46:52 UTC (4,428 KB)
来源：arXiv cs.CL · arxiv.org