Related papers: A General Auxiliary Controller for Multi-agent Flo…

General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…

We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that…

Cooperative multi-agent reinforcement learning (MARL) aims to develop agents that can collaborate effectively. However, most cooperative MARL methods overfit training agents, making learned policies not generalize well to unseen…

Large language models and AI agents have recently shown promise in automating software performance optimization, but existing approaches predominantly rely on local, syntax-driven code transformations. This limits their ability to reason…

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic…

PointGoal Navigation is an embodied task that requires agents to navigate to a specified point in an unseen environment. Wijmans et al. showed that this task is solvable but their method is computationally prohibitive, requiring 2.5 billion…

Through multi-agent competition and the sparse high-level objective of winning a race, we find that both agile flight (e.g., high-speed motion pushing the platform to its physical limits) and strategy (e.g., overtaking or blocking) emerge…

This paper considers a group of mobile autonomous agents moving in Euclidean space with point mass dynamics. We introduce a set of coordination control laws that enable the group to generate the desired stable flocking motion. The control…

While reinforcement learning has made great improvements, state-of-the-art algorithms can still struggle with seemingly simple set-point feedback control problems. One reason for this is that the learned controller may not be able to excite…

The ability to detect faults is an important safety feature for event-based multi-agent systems. In most existing algorithms, each agent tries to detect faults by checking its own behavior. But what if one agent becomes unable to recognize…

This paper addresses the problem of collaboratively satisfying long-term spatial constraints in multi-agent systems. Each agent is subject to spatial constraints, expressed as inequalities, which may depend on the positions of other agents…

Advancements in Large Language Models (LLMs) are revolutionizing the development of autonomous agentic systems by enabling dynamic, context-aware task decomposition and automated tool selection. These sophisticated systems possess…

Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to irreversible errors that cascade through subsequent steps.…

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized…

Due to decelerating gains in single-core CPU performance, computationally expensive simulations are increasingly executed on highly parallel hardware platforms. Agent-based simulations, where simulated entities act with a certain degree of…

Multi-agent, collaborative sensor fusion is a vital component of a multi-national intelligence toolkit. In safety-critical and/or contested environments, adversaries may infiltrate and compromise a number of agents. We analyze state of the…

When dealing with control systems, it is useful and even necessary to assess the performance of underlying transfer functions. The functions may or may not be linear, may or may not be even monotonic. In addition, they may have structural…

Multi-agent path planning is a critical challenge in robotics, requiring agents to navigate complex environments while avoiding collisions and optimizing travel efficiency. This work addresses the limitations of existing approaches by…

In this paper, we investigate the fixed-time behavioral control problem for a team of second-order nonlinear agents, aiming to achieve a desired formation with collision/obstacle~avoidance. In the proposed approach, the two behaviors(tasks)…

We propose a two-component data-driven controller to safely perform docking maneuvers for satellites. Reinforcement Learning is used to deduce an optimal control policy based on measurement data. To safeguard the learning phase, an…