Autonomous agents for desktop automation struggle with complex multi-step tasks due to poor coordination and inadequate quality control. We introduce Agentic Lybic, a novel multi-agent system where the entire architecture operates as a finite-state machine (FSM). This core innovation enables dynamic orchestration. Our system comprises four components: a Controller, a Manager, three Workers (Technician for code-based operations, Operator for GUI interactions, and Analyst for decision support), and an Evaluator. The critical mechanism is the FSM-based routing between these components, which provides flexibility and generalization by dynamically selecting the optimal execution strategy for each subtask. This principled orchestration, combined with robust quality gating, enables adaptive replanning and error recovery. Evaluated officially on the OSWorld benchmark, Agentic Lybic achieves a state-of-the-art 57.07% success rate in 50 steps, substantially outperforming existing methods. Results demonstrate that principled multi-agent orchestration with continuous quality control provides superior reliability for generalized desktop automation in complex computing environments.

Most existing Theory of Mind (ToM) benchmarks for foundation models rely on variations of the Sally-Anne test, offering only a very limited perspective on ToM and neglecting the complexity of human social interactions. To address this gap, we propose ToM-SSI: a new benchmark specifically designed to test ToM capabilities in environments rich with social interactions and spatial dynamics. While current ToM benchmarks are limited to text-only or dyadic interactions, ToM-SSI is multimodal and includes group interactions of up to four agents that communicate and move in situated environments. This unique design allows us to study, for the first time, mixed cooperative-obstructive settings and reasoning about multiple agents' mental state in parallel, thus capturing a wider range of social cognition than existing benchmarks. Our evaluations reveal that the current models' performance is still severely limited, especially in these new tasks, highlighting critical gaps for future research.

The advancement of Large Language Models (LLMs) enables flexible and interpretable automatic evaluations. In the field of machine translation evaluation, utilizing LLMs with translation error annotations based on Multidimensional Quality Metrics (MQM) yields more human-aligned judgments. However, current LLM-based evaluation methods still face challenges in accurately identifying error spans and assessing their severity. In this paper, we propose HiMATE, a Hierarchical Multi-Agent Framework for Machine Translation Evaluation. We argue that existing approaches inadequately exploit the fine-grained structural and semantic information within the MQM hierarchy. To address this, we develop a hierarchical multi-agent system grounded in the MQM error typology, enabling granular evaluation of subtype errors. Two key strategies are incorporated to further mitigate systemic hallucinations within the framework: the utilization of the model's self-reflection capability and the facilitation of agent discussion involving asymmetric information. Empirically, HiMATE outperforms competitive baselines across different datasets in conducting human-aligned evaluations. Further analyses underscore its significant advantage in error span detection and severity assessment, achieving an average F1-score improvement of 89% over the best-performing baseline. We make our code and data publicly available at https://github.com/nlp2ct-shijie/HiMATE.

The concepts of agency and autonomy, pertaining to a system's ability to function effectively, pursue objectives, and self-regulate, are central inquiries across biology, cognitive science, artificial intelligence, and philosophy [1, 2]. Furthermore, previous formalization attempts, largely focused on logical or probabilistic frameworks, have frequently overlooked the inherent limitations imposed by computational constraints on a system's capacity to process information and forecast its environment [6, 7]. This article posits that a deeper understanding of agency can be achieved by examining the fundamental constraints of computation and logic within complex systems. Building upon insights from G odel's incompleteness theorems [8], T uring's work on decidability and com-putability [9], and concepts from thermodynamics and information theory, we formulate a novel explanation. Our core thesis is that genuine autonomy necessarily implies unpredictability from an external perspective: for any truly autonomous system, there exist questions about its future behavior that are fundamentally undecidable. This provides a principled distinction between autonomous and non-autonomous systems without appealing to non-physical properties. We contend that agency specifically emerges in systems operating at the threshold of decidability. Here, G odel-like constraints manifest as the system's inability to internally represent complete 1

Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning (RL)-based subspace exploration strategy provides a novel objective optimization-directed perspective and promising performance. Nevertheless, even with improved performance, current reinforcement learning approaches face challenges similar to conventional methods when dealing with complex datasets. These challenges stem from the inefficient paradigm of using one agent per feature and the inherent complexities present in the datasets. This observation motivates us to investigate and address the above issue and propose a novel approach, namely HRLFS. Our methodology initially employs a Large Language Model (LLM)-based hybrid state extractor to capture each feature's mathematical and semantic characteristics. Based on this information, features are clustered, facilitating the construction of hierarchical agents for each cluster and sub-cluster. Extensive experiments demonstrate the efficiency, scalability, and robustness of our approach. Compared to contemporary or the one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total run time by reducing the number of agents involved.

AI agents thrive when trust is designed in from the start, says vice president of product management at NICE, Neeraj Verma. Automation has become a defining force in the customer experience. Between the chatbots that answer our questions and the recommendation systems that shape our choices, AI-driven tools are now embedded in nearly every interaction. But the latest wave of so-called "agentic AI"--systems that can plan, act, and adapt toward a defined goal--promises to push automation even further. Every single person that I've spoken to has at least spoken to some sort of GenAI bot on their phones. They expect experiences to be not scripted.

Deep neural networks tend to memorize noisy labels, severely degrading their generalization performance. Although Mixup has demonstrated effectiveness in improving generalization and robustness, existing Mixup-based methods typically perform indiscriminate mixing without principled guidance on sample selection and mixing strategy, inadvertently propagating noisy supervision. To overcome these limitations, we propose SelectMix, a confidence-guided mixing framework explicitly tailored for noisy labels. SelectMix first identifies potentially noisy or ambiguous samples through confidence based mismatch analysis using K-fold cross-validation, then selectively blends identified uncertain samples with confidently predicted peers from their potential classes. Furthermore, SelectMix employs soft labels derived from all classes involved in the mixing process, ensuring the labels accurately represent the composition of the mixed samples, thus aligning supervision signals closely with the actual mixed inputs. Through extensive theoretical analysis and empirical evaluations on multiple synthetic (MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100) and real-world benchmark datasets (CIFAR-N, MNIST and Clothing1M), we demonstrate that SelectMix consistently outperforms strong baseline methods, validating its effectiveness and robustness in learning with noisy labels.

Actor-critic algorithms for deep multi-agent reinforcement learning (MARL) typically employ a policy update that responds to the current strategies of other agents. While being straightforward, this approach does not account for the updates of other agents at the same update step, resulting in miscoordination. In this paper, we introduce the $K$-Level Policy Gradient (KPG), a method that recursively updates each agent against the updated policies of other agents, speeding up the discovery of effective coordinated policies. We theoretically prove that KPG with finite iterates achieves monotonic convergence to a local Nash equilibrium under certain conditions. We provide principled implementations of KPG by applying it to the deep MARL algorithms MAPPO, MADDPG, and FACMAC. Empirically, we demonstrate superior performance over existing deep MARL algorithms in StarCraft II and multi-agent MuJoCo.

Personal use of this material is permitted. Abstract--Conventional autonomous trading systems struggle to balance computational efficiency and market responsiveness due to their fixed operating frequency. We propose Hi-DARTS, a hierarchical multi-agent reinforcement learning framework that addresses this trade-off. Hi-DARTS utilizes a meta-agent to analyze market volatility and dynamically activate specialized Time Frame Agents for high-frequency or low-frequency trading as needed. During back-testing on AAPL stock from January 2024 to May 2025, Hi-DARTS yielded a cumulative return of 25.17% with a Sharpe Ratio of 0.75. Our work demonstrates that dynamic, hierarchical agents can achieve superior risk-adjusted returns while maintaining high computational efficiency.

In high-stakes disaster scenarios, timely and informed decision-making is critical yet often challenged by uncertainty, dynamic environments, and limited resources. This paper presents a systematic review of Human-AI collaboration patterns that support decision-making across all disaster management phases. Drawing from 51 peer-reviewed studies, we identify four major categories: Human-AI Decision Support Systems, Task and Resource Coordination, Trust and Transparency, and Simulation and Training. Within these, we analyze sub-patterns such as cognitive-augmented intelligence, multi-agent coordination, explainable AI, and virtual training environments. Our review highlights how AI systems may enhance situational awareness, improves response efficiency, and support complex decision-making, while also surfacing critical limitations in scalability, interpretability, and system interoperability. We conclude by outlining key challenges and future research directions, emphasizing the need for adaptive, trustworthy, and context-aware Human-AI systems to improve disaster resilience and equitable recovery outcomes.