--Autonomous systems operating in unknown environments often rely heavily on visual sensor data, yet making safe and informed control decisions based on these measurements remains a significant challenge. T o facilitate the integration of perception and control in autonomous vehicles, we propose a novel perception-based control approach that incorporates road estimation, quantification of its uncertainty, and uncertainty-aware control based on this estimate. At the core of our method is a parametric road curvature model, optimized using visual measurements of the road through a constrained nonlinear optimization problem. This process ensures adherence to constraints on both model parameters and curvature. By leveraging the Frenet frame formulation, we embed the estimated track curvature into the system dynamics, allowing the controller to explicitly account for perception uncertainty and enhancing robustness to estimation errors based on visual input. We validate our approach in a simulated environment, using a high-fidelity 3D rendering engine, and demonstrate its effectiveness in achieving reliable and uncertainty-aware control for autonomous racing. Robots increasingly rely on visual feedback to navigate and operate in unknown, complex environments. Recent advances demonstrate the potential of visual perception for control tasks [1], [2], enabling robots to make decisions based on high-dimensional sensory inputs. However, safe deployment of autonomous systems requires robust handling of uncertainty throughout the autonomy stack, including perception, planning, and control, to ensure reliability in dynamic and unpredictable settings. Most existing perception-based control methods, however, assume perfect perception and treat its outputs as certain and fully reliable [2], [3]. This decoupled design of the modules can lead to compounding error and cascading failures in safety-critical applications.

While many tools are available for designing AI, non-experts still face challenges in clearly expressing their intent and managing system complexity. We introduce AIAP, a no-code platform that integrates natural language input with visual workflows. AIAP leverages a coordinated multi-agent system to decompose ambiguous user instructions into modular, actionable steps, hidden from users behind a unified interface. A user study involving 32 participants showed that AIAP's AI-generated suggestions, modular workflows, and automatic identification of data, actions, and context significantly improved participants' ability to develop services intuitively. These findings highlight that natural language-based visual programming significantly reduces barriers and enhances user experience in AI service design.

Stackelberg games and their resulting equilibria have received increasing attention in the multi-agent reinforcement learning literature. Each stage of a traditional Stackelberg game involves a leader(s) acting first, followed by the followers. In situations where the roles of leader(s) and followers can be interchanged, the designated role can have considerable advantages, for example, in first-mover advantage settings. Then the question arises: Who should be the leader and when? A bias in the leader selection process can lead to unfair outcomes. This problem is aggravated if the agents are self-interested and care only about their goals and rewards. We formally define this leader selection problem and show its relation to fairness in agents' returns. Furthermore, we propose a multi-agent reinforcement learning framework that maximizes fairness by integrating mediators. Mediators have previously been used in the simultaneous action setting with varying levels of control, such as directly performing agents' actions or just recommending them. Our framework integrates mediators in the Stackelberg setting with minimal control (leader selection). We show that the presence of mediators leads to self-interested agents taking fair actions, resulting in higher overall fairness in agents' returns.

Calibrated trust in automated systems (Lee and See 2004) is critical for their safe and seamless integration into society. Users should only rely on a system recommendation when it is actually correct and reject it when it is factually wrong. One requirement to achieve this goal is an accurate trustworthiness assessment, ensuring that the user's perception of the system's trustworthiness aligns with its actual trustworthiness, allowing users to make informed decisions about the extent to which they can rely on the system (Schlicker et al. 2022). We propose six design guidelines to help designers optimize for accurate trustworthiness assessments, thus fostering ethical and responsible human-automation interactions. The proposed guidelines are derived from existing literature in various fields, such as human-computer interaction, cognitive psychology, automation research, user-experience design, and ethics. We are incorporating key principles from the field of pragmatics, specifically the cultivation of common ground (H. H. Clark 1996) and Gricean communication maxims (Grice 1975). These principles are essential for the design of automated systems because the user's perception of the system's trustworthiness is shaped by both environmental contexts, such as organizational culture or societal norms, and by situational context, including the specific circumstances or scenarios in which the interaction occurs (Hoff and Bashir 2015). Our proposed guidelines provide actionable insights for designers to create automated systems that make relevant trustworthiness cues available. This would ideally foster calibrated trust and more satisfactory, productive, and safe interactions between humans and automated systems. Furthermore, the proposed heuristics might work as a tool for evaluating to what extent existing systems enable users to accurately assess a system's trustworthiness.

Distributed formation maneuver control refers to the problem of maneuvering a group of agents to change their formation shape by adjusting the motions of partial agents, where the controller of each agent only requires local information measured from its neighbors. Although this problem has been extensively investigated, existing approaches are mostly limited to uniform scaling transformations. This article proposes a new type of local matrix-valued constraints, via which non-uniform scaling control of position formation can be achieved by tuning the positions of only two agents (i.e., leaders). Here, the non-uniform scaling transformation refers to scaling the position formation with different ratios along different orthogonal coordinate directions. Moreover, by defining scaling and translation of attitude formation, we propose a distributed control scheme for scaling and translation maneuver control of joint position-attitude formations. It is proven that the proposed controller achieves global convergence, provided that the sensing graph among agents is a 2-rooted bidirectional graph. Compared with the affine formation maneuver control approach, the proposed approach leverages a sparser sensing graph, requires fewer leaders, and additionally enables scaling transformations of the attitude formation. A simulation example is proposed to demonstrate our theoretical results.

Multi-objective reinforcement learning (MORL) plays a pivotal role in addressing multi-criteria decision-making problems in the real world. The multi-policy (MP) based methods are widely used to obtain high-quality Pareto front approximation for the MORL problems. However, traditional MP methods only rely on the online reinforcement learning (RL) and adopt the evolutionary framework with a large policy population. This may lead to sample inefficiency and/or overwhelmed agent-environment interactions in practice. By forsaking the evolutionary framework, we propose the novel Multi-policy Pareto Front Tracking (MPFT) framework without maintaining any policy population, where both online and offline MORL algorithms can be applied. The proposed MPFT framework includes four stages: Stage 1 approximates all the Pareto-vertex policies, whose mapping to the objective space fall on the vertices of the Pareto front. Stage 2 designs the new Pareto tracking mechanism to track the Pareto front, starting from each of the Pareto-vertex policies. Stage 3 identifies the sparse regions in the tracked Pareto front, and introduces a new objective weight adjustment method to fill the sparse regions. Finally, by combining all the policies tracked in Stages 2 and 3, Stage 4 approximates the Pareto front. Experiments are conducted on seven different continuous-action robotic control tasks with both online and offline MORL algorithms, and demonstrate the superior hypervolume performance of our proposed MPFT approach over the state-of-the-art benchmarks, with significantly reduced agent-environment interactions and hardware requirements.

As the reasoning capabilities of Large Language Models (LLMs) continue to advance, LLM-based agent systems offer advantages in flexibility and interpretability over traditional systems, garnering increasing attention. However, despite the widespread research interest and industrial application of agent systems, these systems, like their traditional counterparts, frequently encounter anomalies. These anomalies lead to instability and insecurity, hindering their further development. Therefore, a comprehensive and systematic approach to the operation and maintenance of agent systems is urgently needed. Unfortunately, current research on the operations of agent systems is sparse. To address this gap, we have undertaken a survey on agent system operations with the aim of establishing a clear framework for the field, defining the challenges, and facilitating further development. Specifically, this paper begins by systematically defining anomalies within agent systems, categorizing them into intra-agent anomalies and inter-agent anomalies. Next, we introduce a novel and comprehensive operational framework for agent systems, dubbed Agent System Operations (AgentOps). We provide detailed definitions and explanations of its four key stages: monitoring, anomaly detection, root cause analysis, and resolution.

Recently, Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks. Among them, DeepSeek R1 has garnered significant attention for its exceptional performance and open-source nature, driving advancements in the research of R1-style LRMs. Unlike traditional Large Language Models (LLMs), these models enhance logical deduction and decision-making capabilities during reasoning by incorporating mechanisms such as long chain-of-thought and self-reflection through reinforcement learning. However, with the widespread application of these models, the problem of overthinking has gradually emerged. Specifically, when generating answers, these models often construct excessively long reasoning chains with redundant or repetitive steps, which leads to reduced reasoning efficiency and may affect the accuracy of the final answer. To this end, various efficient reasoning methods have been proposed, aiming to reduce the length of reasoning paths without compromising model performance and reasoning capability. By reviewing the current research advancements in the field of efficient reasoning methods systematically, we categorize existing works into two main directions based on the lens of single-model optimization versus model collaboration: (1) Efficient Reasoning with Single Model, which focuses on improving the reasoning efficiency of individual models; and (2) Efficient Reasoning with Model Collaboration, which explores optimizing reasoning paths through collaboration among multiple models. Besides, we maintain a public GitHub repository that tracks the latest progress in efficient reasoning methods.

Coordinating multiple large language models (LLMs) to solve complex tasks collaboratively poses a fundamental trade-off between the computation costs and collective performance compared with individual model. We introduce a novel, game-theoretically grounded reinforcement learning (RL) framework, the Multi-Agent Cooperation Sequential Public Goods Game (MAC-SPGG), to systematically incen-tivize cooperation in multi-LLM ensembles. In MAC-SPGG, LLM agents move in sequence, observing predecessors' outputs and updating beliefs to condition their own contributions. By redesigning the public-goods reward, effortful contributions become the unique Subgame Perfect Nash Equilibrium (SPNE), which eliminates free-riding under traditional SPGG or PGG. Its sequential protocol replaces costly round-based information exchanges with a streamlined decision flow, cutting communication overhead while retaining strategic depth. We prove the existence and uniqueness of the SPNE under realistic parameters, and empirically show that MAC-SPGG-trained ensembles outperform single-agent baselines, chain-of-thought prompting, and other cooperative methods, even achieving comparable performance to large-scale models across reasoning, math, code generation, and NLP tasks. Our results highlight the power of structured, incentive-aligned MAC-SPGG cooperation for scalable and robust multi-agent language generation.

In scenarios like automated warehouses, assigning tasks to robots presents a heterogeneous multi-task and multi-agent task allocation problem. However, existing task allocation study ignores the integration of multi-task and multi-attribute agent task allocation with heterogeneous task allocation. In addition, current algorithms are limited by scenario constraints and can incur significant errors in specific contexts. Therefore, this study proposes a distributed heterogeneous multi-task and multi-agent task allocation algorithm with a time window, called group consensus-based heterogeneous auction (GCBHA). Firstly, this method decomposes tasks that exceed the capability of a single Agent into subtasks that can be completed by multiple independent agents. And then groups similar or adjacent tasks through a heuristic clustering method to reduce the time required to reach a consensus. Subsequently, the task groups are allocated to agents that meet the conditions through an auction process. Furthermore, the method evaluates the task path cost distance based on the scenario, which can calculate the task cost more accurately. The experimental results demonstrate that GCBHA performs well in terms of task allocation time and solution quality, with a significant reduction in the error rate between predicted task costs and actual costs.