Search NASA⌕ Search

SEARCH · Search NASA

Results for “multi-agent systems”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS2004

Human-Centric Teaming in a Multi-Agent EVA Assembly Task

NASA's Human Space Flight program depends heavily on spacewalks performed by pairs of suited human astronauts. These Extra-Vehicular Activities (EVAs) are severely restricted in both duration and scope by consumables and available manpower.An expanded multi-agent EVA team combining the information-gathering and problem-solving skills of human astronauts with the survivability and physical capabilities of highly dexterous space robots is proposed. A 1-g test featuring two NASA/DARPA Robonaut systems working side-by-side with a suited human subject is conducted to evaluate human-robot teaming strategies in the context of a simulated EVA assembly task based on the STS-61B ACCESS flight experiment.

Rehnmark, Fredrik↗
NASA NTRS2006

Adjustably Autonomous Multi-agent Plan Execution with an Internal Spacecraft Free-Flying Robot Prototype

We present an multi-agent model-based autonomy architecture with monitoring, planning, diagnosis, and execution elements. We discuss an internal spacecraft free-flying robot prototype controlled by an implementation of this architecture and a ground test facility used for development. In addition, we discuss a simplified environment control life support system for the spacecraft domain also controlled by an implementation of this architecture. We discuss adjustable autonomy and how it applies to this architecture. We describe an interface that provides the user situation awareness of both autonomous systems and enables the user to dynamically edit the plans prior to and during execution as well as control these agents at various levels of autonomy. This interface also permits the agents to query the user or request the user to perform tasks to help achieve the commanded goals. We conclude by describing a scenario where these two agents and a human interact to cooperatively detect, diagnose and recover from a simulated spacecraft fault.

Dorais, Gregory A.↗
DOE OSTI2026

ToPolyAgent: AI agents for coarse-grained bead-spring topological polymer simulations

We introduce ToPolyAgent, a multi-agent AI framework for performing coarse-grained molecular dynamics (MD) simulations of topological polymers through natural language instructions. By integrating large language models (LLMs) with domain-specific computational tools, ToPolyAgent supports both interactive and autonomous simulation workflows across diverse polymer architectures, including linear, ring, brush, and star polymers, as well as dendrimers. The system consists of four LLM-powered agents: a Config Agent for generating initial polymer–solvent configurations, a Simulation Agent for executing LAMMPS-based MD simulations and conformational analyses, a Report Agent for compiling markdown reports, and a Workflow Agent for streamlined autonomous operations. Interactive mode incorporates user feedback loops for iterative refinements, while autonomous mode enables end-to-end task execution from detailed prompts. We demonstrate ToPolyAgent's versatility through case studies involving diverse polymer architectures under varying solvent conditions, thermostats, and simulation lengths. Furthermore, we highlight its potential as a research assistant by directing it to investigate the effect of interaction parameters on the linear polymer conformation, and the influence of grafting density on the persistence length of the brush polymer. By coupling natural language interfaces with rigorous simulation tools, ToPolyAgent lowers barriers to complex computational workflows and advances AI-driven materials discovery in polymer science. It lays the foundation for autonomous and extensible multi-agent scientific research ecosystems.

Ding, Lijie [Oak Ridge National Laboratory (ORNL),↗
DOE OSTI2025

CityLearn v2: energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communities

As more distributed energy resources become part of the demand-side infrastructure, quantifying their energy flexibility on a community scale is crucial. CityLearn v1 provided an environment for benchmarking control algorithms. However, there is no standardized environment utilizing realistic building-stock datasets for distributed energy resource control benchmarking without co-simulation or third-party frameworks. CityLearn v2 extends CityLearn v1 by providing a stand-alone simulation environment that leverages the End-Use Load Profiles for the U.S. Building Stock dataset to create grid-interactive communities for resilient, multi-agent, and objective control of distributed energy resources with dynamic occupant feedback. While the v1 environment used pre-simulated building thermal loads, the v2 environment uses data-driven thermal dynamics and eliminates the need for co-simulation with building energy performance software. This work details the v2 environment and provides application examples that use reinforcement learning control to manage battery energy storage system, vehicle-to-grid control, and thermal comfort during heat pump power modulation.

Nweye, Kingsley↗
NASA NTRS2006

QUICR-learning for Multi-Agent Coordination

Coordinating multiple agents that need to perform a sequence of actions to maximize a system level reward requires solving two distinct credit assignment problems. First, credit must be assigned for an action taken at time step t that results in a reward at time step t > t. Second, credit must be assigned for the contribution of agent i to the overall system performance. The first credit assignment problem is typically addressed with temporal difference methods such as Q-learning. The second credit assignment problem is typically addressed by creating custom reward functions. To address both credit assignment problems simultaneously, we propose the "Q Updates with Immediate Counterfactual Rewards-learning" (QUICR-learning) designed to improve both the convergence properties and performance of Q-learning in large multi-agent problems. QUICR-learning is based on previous work on single-time-step counterfactual rewards described by the collectives framework. Results on a traffic congestion problem shows that QUICR-learning is significantly better than a Q-learner using collectives-based (single-time-step counterfactual) rewards. In addition QUICR-learning provides significant gains over conventional and local Q-learning. Additional results on a multi-agent grid-world problem show that the improvements due to QUICR-learning are not domain specific and can provide up to a ten fold increase in performance over existing methods.

Agogino, Adrian K.↗
NASA NTRS2005

A Scalable and Robust Multi-Agent Approach to Distributed Optimization

Modularizing a large optimization problem so that the solutions to the subproblems provide a good overall solution is a challenging problem. In this paper we present a multi-agent approach to this problem based on aligning the agent objectives with the system objectives, obviating the need to impose external mechanisms to achieve collaboration among the agents. This approach naturally addresses scaling and robustness issues by ensuring that the agents do not rely on the reliable operation of other agents We test this approach in the difficult distributed optimization problem of imperfect device subset selection [Challet and Johnson, 2002]. In this problem, there are n devices, each of which has a "distortion", and the task is to find the subset of those n devices that minimizes the average distortion. Our results show that in large systems (1000 agents) the proposed approach provides improvements of over an order of magnitude over both traditional optimization methods and traditional multi-agent methods. Furthermore, the results show that even in extreme cases of agent failures (i.e., half the agents fail midway through the simulation) the system remains coordinated and still outperforms a failure-free and centralized optimization algorithm.

Tumer, Kagan↗
DOE OSTI2026

Toward Intelligent Multimodal Holography for Real-Time Chemical Imaging of Dynamic Ion Separation

Molecular-level visualization of ion transport and separation dynamics in complex environments is crucial for advancing energy systems, water purification, and critical materials recovery. Achieving this requires imaging platforms that combine structural sensitivity, chemical specificity, and real-time operation. Digital off-axis holography (DOAH) provides high-throughput, label-free quantitative phase imaging but inherently lacks chemical selectivity. Integrating DOAH with complementary spectroscopic channels such as fluorescence or hyperspectral imaging introduces the needed molecular specificity, while also creating challenges in multimodal data fusion, synchronization, and computational throughput. Artificial intelligence offers a powerful route to address these limitations by uniting physics-based reconstruction with data-driven interpretation. In this Perspective, we outline a framework for intelligent multimodal holography and demonstrate its potential using a preliminary AI-driven test case. Raw DOAH holograms of lanthanide solutions subjected to magnetic field gradients were analyzed using multi-agent AI workflows that autonomously selected reconstruction tools, extracted NMF components, and generated scientific claims consistent with true paramagnetic and diamagnetic behavior. This demonstration shows how AI-enabled reasoning can deliver real-time chemical–structural interpretation directly from raw holograms. Together, these advances define a path toward adaptive, intelligent holography platforms capable of supporting in situ chemical separations, dynamic ion transport analysis, and next-generation interfacial science.

Ricchiuti, Giovanna↗
NASA NTRS1992

Multi-agent planning and scheduling, execution monitoring and incremental rescheduling: Application to motorway traffic

This article describes a planning method applicable to agents with great perception and decision-making capabilities and the ability to communicate with other agents. Each agent has a task to fulfill allowing for the actions of other agents in its vicinity. Certain simultaneous actions may cause conflicts because they require the same resource. The agent plans each of its actions and simultaneously transmits these to its neighbors. In a similar way, it receives plans from the other agents and must take account of these plans. The planning method allows us to build a distributed scheduling system. Here, these agents are robot vehicles on a highway communicating by radio. In this environment, conflicts between agents concern the allocation of space in time and are connected with the inertia of the vehicles. Each vehicle made a temporal, spatial, and situated reasoning in order to drive without collision. The flexibility and reactivity of the method presented here allows the agent to generate its plan based on assumptions concerning the other agents and then check these assumptions progressively as plans are received from the other agents. A multi-agent execution monitoring of these plans can be done, using data generated during planning and the multi-agent decision-making algorithm described here. A selective backtrack allows us to perform incremental rescheduling.

Mourou, Pascal↗
DOE OSTI2025

The Cost of Scaling Up in Large-Format Additive Manufacturing

Additive manufacturing (AM) of large objects has, over the last decade, required the scaling of existing material extrusion processes. The current generation of large-scale printers are primarily gantry robots with high-throughput extrusion systems. With workspaces approaching 50 m 3 , these printers have pushed the boundaries of achievable print volume while allowing the utilization of low-cost feedstocks, such as cementitious materials and polymer pellets, like those used in injection molding. Continued workspace expansion requires an examination of the inherent trade-offs, which impact capital and operational costs. Here, in this work, the authors examine these trade-offs to determine fundamental scaling laws for existing system architectures, survey the state of the art for alternative system configurations, and pose recommendations for future system designers to continue the evolution of large-scale AM systems.

3D printing↗
DOE OSTI2025

Multi-agent AI collaboration for digital twin development and assessment

Developing a digital twin (DT) model involves different steps that encompass formulating requirements, model development, implementation, and assessment with respect to real applications. Human expertise is required to coordinate and implement different steps in the DT development and assessment process. However, certain parts of this process can be automated using artificial intelligence (AI) agents for efficient workflow development. In this work, we test and analyze a multiagent AI collaboration with humans in the loop to automate different elements of the DT development and assessment process. To implement the workflow for multiagent AI DT development and assessment, we use Autogen, a multiagent framework developed by Microsoft. Autogen offers a modular and flexible framework for configuring and designing task-specific multiagent workflows. In this framework, large language models (LLMs) form the core intelligence of the AI agents where the quality and performance of the automated element is governed by the inherent capabilities and knowledge base of the LLM. We use retrieval augmented generation to supplement the LLM with relevant domain-specific information for DT requirement formulation. We illustrate this multiagent workflow using a case study on a thermal energy storage system, focusing on how AI agents can collaborate with humans to expedite and optimize different elements of DT development and assessment process.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Nuclear microreactor transient and load-following control with deep reinforcement learning

The economic feasibility of nuclear microreactors will depend on minimizing operating costs through advancements in autonomous control, especially when these microreactors are operating alongside other types of energy systems (e.g., renewable energy). This study explores the application of deep reinforcement learning (RL) for real-time drum control in microreactors, exploring performance in regard to load-following scenarios. By leveraging a point kinetics model with thermal and xenon feedback, we first establish a baseline using a single-output RL agent, then compare it against a traditional proportional–integral–derivative (PID) controller. This study demonstrates that RL controllers, including both single- and multi-agent RL (MARL) frameworks, can achieve similar or even superior load-following performance as traditional PID control across a range of load-following scenarios. In short transients, the RL agent was able to reduce the tracking error rate in comparison to PID by one half to one third. Over extended 300-minute load-following scenarios in which xenon feedback becomes a dominant factor, PID maintained better accuracy, but RL still remained within a 1% error margin despite being trained only on short-duration scenarios. This highlights RL’s strong ability to generalize and extrapolate to longer, more complex transients, affording substantial reductions in training costs and reduced overfitting. Furthermore, when control was extended to multiple drums, MARL enabled independent drum control as well as maintained reactor symmetry constraints without sacrificing performance---an objective that standard single-agent RL could not learn. We also found that, as increasing levels of Gaussian noise were added to the power measurements, the RL controllers were able to maintain lower error rates than PID, and to do so with at least 10% and upwards of 150% less control effort. These findings illustrate RL's potential for autonomous nuclear reactor control, laying the groundwork for future integration into high-fidelity simulations and experimental validation efforts.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

mada-tools: MCP servers, configurations, skills, and examples for MADA

MADA-tools (Multi-Agent Design Assistant tools) is a library for defining MCP (Model Context Protocol) servers that can be used by AI agents in the MADA project. Each MCP server provides a focused set of tools that enhances an LLM's knowledge and capabilities for a specific domain, for example, how to launch jobs with Flux versus Slurm. The library makes it easy to configure and start multiple MCP servers using configuration files or command line options. Once running, these servers are intended to be consumed by one or more agents in the MADA ecosystem. The system is designed to be extensible so that future projects can contribute their own MCP servers, skills, and toolsets.

Gunnarson, BrianS [Lawrence Livermore National Lab↗
DOE OSTI2026

Building MCP-native hierarchical AI scientist ecosystems: a perspective on scaling multi-agent scientific discovery

Large language models (LLMs) are evolving from chatbots with limited tool-using capabilities to agentic AI systems that can perform deep research, assist in proposing hypotheses, help design experiments, automate data analysis, and draft scientific reports. However, there are currently two bottlenecks limiting LLMs' real-world impact on the broader scientific research community beyond academic demonstrations: lack of interoperability (repetitive manual tool-integration is required across scenarios) and the need for scalable coordination (unstructured communication and memory become brittle as the number of agents grows). In this Perspective, we argue that the next phase of agentic scientific discovery requires the development of an ecosystem of protocol-native agents and tools organized through hierarchies inspired by human society, beyond the current paradigm of a single monolithic “AI scientist”. We use Model Context Protocol (MCP) as a concrete example of an emerging interoperability layer for scientific tool and context exchange, and we propose three complementary pathways to increase the scaling capabilities of an MCP-native scientific ecosystem by addressing the composability issues: (1) MCP servers for high-value scientific tools maintained by domain experts, (2) automated transformation of existing code repositories into MCP services, and (3) autonomous invention and evolution of new agents and workflows. Finally, we provide a practical roadmap for scaling AI-driven scientific discovery by expanding tool supply and coordination in MCP-native scientific ecosystems.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2001

Design and Control of Large Collections of Learning Agents

The intelligent control of multiple autonomous agents is an important yet difficult task. Previous methods used to address this problem have proved to be either too brittle, too hard to use, or not scalable to large systems. The 'Collective Intelligence' project at NASA/Ames provides an elegant, machine-learning approach to address these problems. This approach mathematically defines some essential properties that a reward system should have to promote coordinated behavior among reinforcement learners. This work has focused on creating additional key properties and algorithms within the mathematics of the Collective Intelligence framework. One of the additions will allow agents to learn more quickly, in a more coordinated manner. The other will let agents learn with less knowledge of their environment. These additions will allow the framework to be applied more easily, to a much larger domain of multi-agent problems.

Agogino, Adrian↗
NASA NTRS2004

Planning and Execution: The Spirit of Opportunity for Robust Autonomous Systems

One of the most exciting endeavors pursued by human kind is the search for life in the Solar System and the Universe at large. NASA is leading this effort by designing, deploying and operating robotic systems that will reach planets, planet moons, asteroids and comets searching for water, organic building blocks and signs of past or present microbial life. None of these missions will be achievable without substantial advances in.the design, implementation and validation of autonomous control agents. These agents must be capable of robustly controlling a robotic explorer in a hostile environment with very limited or no communication with Earth. The talk focuses on work pursued at the NASA Ames Research center ranging from basic research on algorithm to deployed mission support systems. We will start by discussing how planning and scheduling technology derived from the Remote Agent experiment is being used daily in the operations of the Spirit and Opportunity rovers. Planning and scheduling is also used as the fundamental paradigm at the core of our research in real-time autonomous agents. In particular, we will describe our efforts in the Intelligent Distributed Execution Architecture (IDEA), a multi-agent real-time architecture that exploits artificial intelligence planning as the core reasoning engine of an autonomous agent. We will also describe how the issue of plan robustness at execution can be addressed by novel constraint propagation algorithms capable of giving the tightest exact bounds on resource consumption or all possible executions of a flexible plan.

Muscettola, Nicola↗
NASA NTRS2005

Acquisition of Autonomous Behaviors by Robotic Assistants

Our research achievements under the NASA-JSC grant contributed significantly in the following areas. Multi-agent based robot control architecture called the Intelligent Machine Architecture (IMA) : The Vanderbilt team received a Space Act Award for this research from NASA JSC in October 2004. Cognitive Control and the Self Agent : Cognitive control in human is the ability to consciously manipulate thoughts and behaviors using attention to deal with conflicting goals and demands. We have been updating the IMA Self Agent towards this goal. If opportunity arises, we would like to work with NASA to empower Robonaut to do cognitive control. Applications 1. SES for Robonaut, 2. Robonaut Fault Diagnostic System, 3. ISAC Behavior Generation and Learning, 4. Segway Research.

Peters, R. A., II↗
NASA NTRS2005

Distributed Evaluation Functions for Fault Tolerant Multi-Rover Systems

The ability to evolve fault tolerant control strategies for large collections of agents is critical to the successful application of evolutionary strategies to domains where failures are common. Furthermore, while evolutionary algorithms have been highly successful in discovering single-agent control strategies, extending such algorithms to multiagent domains has proven to be difficult. In this paper we present a method for shaping evaluation functions for agents that provide control strategies that both are tolerant to different types of failures and lead to coordinated behavior in a multi-agent setting. This method neither relies of a centralized strategy (susceptible to single point of failures) nor a distributed strategy where each agent uses a system wide evaluation function (severe credit assignment problem). In a multi-rover problem, we show that agents using our agent-specific evaluation perform up to 500% better than agents using the system evaluation. In addition we show that agents are still able to maintain a high level of performance when up to 60% of the agents fail due to actuator, communication or controller faults.

Agogino, Adrian↗