Graph-as-Policy (GaP) is introduced, a multi-agent coding harness that generates directed computation graphs with perception, planning, and control nodes from a Modular Open Robot Skill Library (MORSL), and can achieve success rates that significantly outperform baselines.
Abstract
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
Modern manufacturing faces increasing demands for flexibility, customization, and productivity under dynamic conditions. Multi-robot systems offer a promising solution by enabling cooperative execution of complex tasks, such as assembly and cooperative manipulation. In this context, Multi-Agent Reinforcement Learning (MARL) has emerged as a promising paradigm to enhance coordination and adaptability in industrial settings. MARL enables multiple agents to learn and interact in shared environments to achieve common goals within complex and dynamic industrial processes. In this paper, a deep analysis of MARL applied to industrial multi-robot systems based on a systematic review is presented, with particular focus on cooperative manipulation tasks. Following PRISMA guidelines, we analyze a total of 30 articles published between 2016 and 2026, selected independently by two of the authors from an initial pool of 102 records retrieved from Scopus and Web of Science. These articles were used to address five key questions regarding MARL algorithms, control architectures, industrial applications and validation practices. These research questions seek to examine gaps and trends at the research level which are important for the development of multi-agent control technologies. This review shows a clear prevalence of model-free algorithms under Centralized Training with Decentralized Execution (CTDE) architectures, with validation mainly performed in simulation. Despite promising results and high potential for impact, critical gaps remain in scalability, reproducibility, and sim-to-real transfer, limiting real deployment in manufacturing environments. To address these challenges and fill current gaps, we outline actionable research directions, such as hybrid MARL approaches, standardized industrial benchmarks, digital twin pipelines, and safety-aware deployment strategies, to accelerate MARL adoption in industrial environments.
Francisco J. Huertos, Oihane Bañales, Pedro Álvarez et al.· Robotics· 0 citations
M3W is a novel approach that applies mixture-of-experts (MoE) to world model instead of policy, enabling both learning and planning, and demonstrates superior performance, sample efficiency, and multi-task adaptability.
Zi-Jie Zhao, Zhong Zhao, Kaixuan Xu et al.· Neural Information Processin...· 9 citations
End-to-end vision-language-action (VLA) and world-action models offer an elegant route to general-purpose robotics, but their reliability is bounded by validated physical coverage. When an unfamiliar object, sensor, embodiment, or contact falls outside that coverage and no validated fallback exists, correcting the failure requires new robot data, a policy update, and regression testing. This recurring burden is the retraining tax. Unlike text, embodied data must often be created by operating machines. We present Teach-and-Grow Learning (TGL), an agent-centered architecture for general robot learning. In its general form, a multimodal agent turns a few successful demonstrations into reusable Skill Blocks: closed-loop behaviors for meaningful subgoals. In a new scene, the agent grounds and composes these blocks, selects learned or geometric tools, observes the physical outcome, and revises the route when execution departs from intent. A Skill Library stores executable behavior, while structured Experience Memory carries forward success, failure, and repair. New tasks are acquired without task-specific policy retraining. Our LIBERO evaluation attains state-of-the-art performance; controlled studies expose skill induction, persistent reuse, and agent-directed adaptation. Finally, we propose the Teach-and-Grow scaling-law hypothesis: if X denotes effective reusable experience, future-task error and teaching demand should approach irreducible floors as power laws in X. The architecture therefore treats deployment as a period of continued learning, in which one task can make the next easier.
This short paper revisits the Push-T task in the context of emerging advances in Agentic Robotics where an LLM coding agent -- Claude Code with Fable 5 -- is prompted to create an algorithmic solution that does not require any demonstration data.
Shuang-Yu Xie, Kai-Peng Chen, Ken Goldberg· 0 citations
: This paper provides a thorough survey and integrative presentation of cooperative path planning for multi-robot systems operating in dynamic, cluttered, and partially observable environments. People synthesise algorithmic foundations ranging from heuristic graph search to sampling-based motion planners, including A*, D* Lite, and Safe Interval Path Planning for discrete/time-augmented spaces, as well as RRT, RRT*, and Informed RRT* for continuous configuration spaces. Multi-agent coordination techniques are reviewed, covering reciprocal collision avoidance (ORCA) and centralised Multi-Agent Path Finding (MAPF) solvers such as Conflict-Based Search (CBS) and bounded-suboptimal variants (ECBS). The paper also examine control and safety layers like Model Predictive Control and Control Barrier Functions that translate plans into dynamically feasible commands with safety guarantees. Recent progress in cooperative multi-agent reinforcement learning (MAPPO, QMIX, MADDPG) is evaluated for adaptability under partial observability and nonstationary environments. Applications in warehousing, intelligent transportation, and disaster response are used to illustrate practical trade-offs and integration patterns, referencing real-world systems such as Kiva-style warehouse fleets and autonomous driving pipelines. The paper concludes with a focused discussion on open challenges — scalability with guarantees, safety under uncertainty, sim-to-real transfer, and planning – control interface fragility — and proposes research directions including learning-augmented heuristics, unified safety-aware planning, adaptive MPC – CBF filters, and more informative benchmarks to drive reproducible progress.
Yun Pan· Proceedings of the 3rd Inter...· 0 citations
Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collisions. Signal Temporal Logic (STL) elegantly encodes such objectives, but current STL planning methods face critical limitations. State-of-the-art optimization-based approaches can handle arbitrary STL specifications but struggle with scalability, becoming computationally impractical as the number of agents grows. Learning-based methods efficiently handle a large number of agents with rapid planning times but fare poorly when deployment-time objectives differ from those used during training, and do not support planning tasks that require different specifications to be ascribed to different agents (i.e., heterogeneity) or team-level specifications requiring coordination of multiple agents. This fundamental trade-off between generalizability and scalability presents a challenge for realizing multi-agent STL planning algorithms in practice. To overcome this challenge, we introduce a new diffusion method for multi-agent planning with STL specifications. Using a differentiable approximation of STL, we integrate the STL gradient in the denoising process, making our approach generalizable to novel formulas whose predicates are placed anywhere within the goal region covered during training, while achieving the same scalability as existing learning-based methods. Our method supports heterogeneous specifications, and by using diffusion models, naturally enhances plan diversity, thereby significantly reducing safety-related violations (e.g., collisions) among agents. A detailed evaluation study justifies the utility of STL-guided diffusion-based multi-agent planners for constructing generalizable, scalable, and diverse plans. Videos and code are available at https://www.jeappen.com/diff-ma-stl/ and https://github.com/jeappen/diff-ma-stl .
Joe Eappen, Zikang Xiong, S. Iyengar et al.· IEEE Robotics and Automation...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
