This paper considers the problem of decentralized optimization on compact submanifolds, where a finite sum of smooth (possibly non-convex) local functions is minimized by $n$ agents forming an undirected and connected graph. However, the efficiency of distributed optimization is often hindered by communication bottlenecks. To mitigate this, we propose the Quantized Riemannian Gradient Tracking (Q-RGT) algorithm, where agents update their local variables using quantized gradients. The introduction of quantization noise allows our algorithm to bypass the constraints of the accurate Riemannian projection operator (such as retraction), further improving iterative efficiency. To the best of our knowledge, this is the first algorithm to achieve an $\mathcal{O}(1/K)$ convergence rate in the presence of quantization, matching the convergence rate of methods without quantization. Additionally, we explicitly derive lower bounds on decentralized consensus associated with a function of quantization levels. Numerical experiments demonstrate that Q-RGT performs comparably to non-quantized methods while reducing communication bottlenecks and computational overhead.

Instance Image-Goal Navigation (IIN) requires autonomous agents to identify and navigate to a target object or location depicted in a reference image captured from any viewpoint. While recent methods leverage powerful novel view synthesis (NVS) techniques, such as three-dimensional Gaussian splatting (3DGS), they typically rely on randomly sampling multiple viewpoints or trajectories to ensure comprehensive coverage of discriminative visual cues. This approach, however, creates significant redundancy through overlapping image samples and lacks principled view selection, substantially increasing both rendering and comparison overhead. In this paper, we introduce a novel IIN framework with a hierarchical scoring paradigm that estimates optimal viewpoints for target matching. Our approach integrates cross-level semantic scoring, utilizing CLIP-derived relevancy fields to identify regions with high semantic similarity to the target object class, with fine-grained local geometric scoring that performs precise pose estimation within promising regions. Extensive evaluations demonstrate that our method achieves state-of-the-art performance on simulated IIN benchmarks and real-world applicability.

The increasing complexity of modern manufacturing, coupled with demand fluctuation, supply chain uncertainties, and product customization, underscores the need for manufacturing systems that can flexibly update their configurations and swiftly adapt to disturbances. However, current research falls short in providing a holistic reconfigurable manufacturing framework that seamlessly monitors system disturbances, optimizes alternative line configurations based on machine capabilities, and automates simulation evaluation for swift adaptations. This paper presents a dynamic manufacturing line reconfiguration framework to handle disturbances that result in operation time changes. The framework incorporates a system process digital twin for monitoring disturbances and triggering reconfigurations, a capability-based ontology model capturing available agent and resource options, a configuration optimizer generating optimal line configurations, and a simulation generation program initializing simulation setups and evaluating line configurations at approximately 400x real-time speed. A case study of a battery production line has been conducted to evaluate the proposed framework. In two implemented disturbance scenarios, the framework successfully recovers system throughput with limited resources, preventing the 26% and 63% throughput drops that would have occurred without a reconfiguration plan. The reconfiguration optimizer efficiently finds optimal solutions, taking an average of 0.03 seconds to find a reconfiguration plan for a manufacturing line with 51 operations and 40 available agents across 8 agent types.

Model Predictive Path Integral (MPPI) controller is used to solve unconstrained optimal control problems and Control Barrier Function (CBF) is a tool to impose strict inequality constraints, a.k.a, barrier constraints. In this work, we propose an integration of these two methods that employ CBF-like conditions to guide the control sampling procedure of MPPI. CBFs provide an inequality constraint restricting the rate of change of barrier functions by a classK function of the barrier itself. We instead impose the CBF condition as an equality constraint by choosing a parametric linear classK function and treating this parameter as a state in an augmented system. The time derivative of this parameter acts as an additional control input that is designed by MPPI. A cost function is further designed to reignite Nagumo's theorem at the boundary of the safe set by promoting specific values of classK parameter to enforce safety. Our problem formulation results in an MPPI subject to multiple state and control-dependent equality constraints which are non-trivial to satisfy with randomly sampled control inputs. We therefore also introduce state transformations and control projection operations, inspired by the literature on path planning for manifolds, to resolve the aforementioned issue. We show empirically through simulations and experiments on quadrotor that our proposed algorithm exhibits better sampled efficiency and enhanced capability to operate closer to the safe set boundary over vanilla MPPI.

We consider the Multi-Robot Task Allocation (MRTA) problem that aims to optimize an assignment of multiple robots to multiple tasks in challenging environments which are with densely populated obstacles and narrow passages. In such environments, conventional methods optimizing the sum-of-cost are often ineffective because the conflicts between robots incur additional costs (e.g., collision avoidance, waiting). Also, an allocation that does not incorporate the actual robot paths could cause deadlocks, which significantly degrade the collective performance of the robots. We propose a scalable MRTA method that considers the paths of the robots to avoid collisions and deadlocks which result in a fast completion of all tasks (i.e., minimizing the \textit{makespan}). To incorporate robot paths into task allocation, the proposed method constructs a roadmap using a Generalized Voronoi Diagram. The method partitions the roadmap into several components to know how to redistribute robots to achieve all tasks with less conflicts between the robots. In the redistribution process, robots are transferred to their final destinations according to a push-pop mechanism with the first-in first-out principle. From the extensive experiments, we show that our method can handle instances with hundreds of robots in dense clutter while competitors are unable to compute a solution within a time limit.

Modern data marketplaces and data sharing consortia increasingly rely on incentive mechanisms to encourage agents to contribute data. However, schemes that reward agents based on the quantity of submitted data are vulnerable to manipulation, as agents may submit fabricated or low-quality data to inflate their rewards. Prior work has proposed comparing each agent's data against others' to promote honesty: when others contribute genuine data, the best way to minimize discrepancy is to do the same. Yet prior implementations of this idea rely on very strong assumptions about the data distribution (e.g. Gaussian), limiting their applicability. In this work, we develop reward mechanisms based on a novel, two-sample test inspired by the Cramér-von Mises statistic. Our methods strictly incentivize agents to submit more genuine data, while disincentivizing data fabrication and other types of untruthful reporting. We establish that truthful reporting constitutes a (possibly approximate) Nash equilibrium in both Bayesian and prior-agnostic settings. We theoretically instantiate our method in three canonical data sharing problems and show that it relaxes key assumptions made by prior work. Empirically, we demonstrate that our mechanism incentivizes truthful data sharing via simulations and on real-world language and image data.

Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environments. However, despite LLMs' advanced abilities and the sophisticated modular design of agentic methods, existing LLM-based planning algorithms remain limited by weak adaptation capabilities to multi-agent embodied scenarios. We address this limitation by introducing a framework that enables LLM agents to learn and evolve both before and during test time, equipping them with environment-relevant knowledge for better planning and enhanced communication for improved cooperation. Inspired by centralized training with decentralized execution in multi-agent reinforcement learning, we propose a \textit{Learn as Individuals, Evolve as a Team (LIET)} paradigm for multi-agent LLMs adaptation. At the individual level, LLM agents learn a local utility function from exploratory datasets to better comprehend the embodied environment, which is then queried during test time to support informed decision-making. At the team level, LLM agents collaboratively and iteratively maintain and update a shared cooperation knowledge list based on new experiences, using it to guide more effective communication. By combining individual learning with team evolution, LIET enables comprehensive and flexible adaptation for LLM agents. Our experiments on Communicative Watch-And-Help and ThreeD-World Multi-Agent Transport benchmarks demonstrate that LIET, instantiated with both LLaMA and GPT-4o, outperforms existing baselines and exhibits strong cooperative planning abilities.

In the realm of embodied intelligence, the evolution of large language models (LLMs) has markedly enhanced agent decision making. Consequently, researchers have begun exploring agent performance in dynamically changing high-risk scenarios, i.e ., fire, flood, and wind scenarios in the HAZARD benchmark. Under these extreme conditions, the delay in decision making emerges as a crucial yet insufficiently studied issue. W e propose a Time Conversion Mechanism (TCM) that translates inference delays in decision-making into equivalent simulation frames, thus aligning cognitive and physical costs under a single FPS-based metric. By extending HAZARD with Respond Latency (RL) and Latency-to-Action Ratio (LAR), we deliver a fully latency-aware evaluation protocol. Moreover, we present the Rapid-Reflex Async-Reflect Agent (RRARA), which couples a lightweight LLM-guided feedback module with a rule-based agent to enable immediate reactive behaviors and asynchronous reflective refinements in situ. Experiments on HAZARD show that RRARA substantially outperforms existing baselines in latency-sensitive scenarios.

Dual-arm robots play a crucial role in improving efficiency and flexibility in complex multitasking scenarios. While existing methods have achieved promising results in task planning, they often fail to fully optimize task parallelism, limiting the potential of dual-arm collaboration. To address this issue, we propose RoboPARA, a novel large language model (LLM)-driven framework for dual-arm task parallelism planning. RoboPARA employs a two-stage process: (1) Dependency Graph-based Planning Candidates Generation, which constructs directed acyclic graphs (DAGs) to model task dependencies and eliminate redundancy, and (2) Graph Re-Traversal-based Dual-Arm Parallel Planning, which optimizes DAG traversal to maximize parallelism while maintaining task coherence. In addition, we introduce the Cross-Scenario Dual-Arm Parallel Task dataset (X-DAPT dataset), the first dataset specifically designed to evaluate dual-arm task parallelism across diverse scenarios and difficulty levels. Extensive experiments on the X-DAPT dataset demonstrate that RoboPARA significantly outperforms existing methods, achieving higher efficiency and reliability, particularly in complex task combinations. The code and dataset will be released upon acceptance.

Researchers worried about catastrophic risks from advanced AI have argued that we should expect sufficiently capable AI agents to pursue power over humanity because power is a convergent instrumental goal, something that is useful for a wide range of final goals. Others have recently expressed skepticism of these claims. This paper aims to formalize the concepts of instrumental convergence and power-seeking in an abstract, decision-theoretic framework, and to assess the claim that power is a convergent instrumental goal. I conclude that this claim contains at least an element of truth, but might turn out to have limited predictive utility, since an agent's options cannot always be ranked in terms of power in the absence of substantive information about the agent's final goals. However, the fact of instrumental convergence is more predictive for agents who have a good shot at attaining absolute or near-absolute power.