From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a multi-agent framework that systematically identifies biases by disentangling each statement as fact or opinion, assigning a bias intensity score, and providing concise, factual justifications. Evaluated on 1,500 samples from the WikiNPOV dataset, the framework achieves 84.9% accuracy$\unicode{x2014}$an improvement of 13.0% over the zero-shot baseline$\unicode{x2014}$demonstrating the efficacy of explicitly modeling fact versus opinion prior to quantifying bias intensity. By combining enhanced detection accuracy with interpretable explanations, this approach sets a foundation for promoting fairness and accountability in modern language models.

Recently, Devin has made a significant buzz in the Artificial Intelligence (AI) community as the world's first fully autonomous AI software engineer, capable of independently developing software code [1] [2]. Devin uses the concept of agentic workflow in Generative AI (GenAI), which empowers AI agents to engage in a more dynamic, iterative, and self-reflective process. With Saarthi, verification engineers can focus on more complex problems, and verification teams can strive for more ambitious goals. The domain-agnostic implementation of Saarthi makes it scalable for use across various domains such as RTL design, UVM-based verification, and others. Hardware design verification, especially formal verification, entails a methodical and disciplined approach to the planning, development, execution, and sign-off of functionally correct hardware designs. Formal verification uses mathematical methods to prove the correctness of hardware designs against their specifications, ensuring that all possible states and inputs are considered, which complements traditional simulation-based verification techniques that might only cover a subset of possible scenarios due to practical constraints [3]. The formal verification process encompasses several key roles, such as organizational coordination, task allocation, code development, property proving, analyzing Counter Examples (CEXs), debugging, coverage closure, and documentation preparation. These roles are crucial for managing the complexity and ensuring the thoroughness of the verification process. For instance, analyzing counterexamples involves identifying specific scenarios where the design might fail to meet its specifications, which is critical for debugging and refining the design. This highly intricate activity demands meticulous attention to detail, given its long development cycles and the critical nature of ensuring hardware functionality and reliability [4]. The field of Natural Language Processing (NLP) has undergone a significant transformation with the advent of Large Language Models (LLMs) [5].

The release of ChatGPT by OpenAI in November 2022 marked another significant milestone in the evolution of AI. ChatGPT, a large language model capable of generating human-like text, demonstrated the potential of AI to understand and generate natural language. This capability opened up new possibilities for AI applications, from customer service to content creation. The world responded to ChatGPT with a mix of awe and excitement, recognizing the potential of AI to transform how humans communicate and interact with technology to enhance our lives. Today, the rise of agentic AI -- systems capable of advanced reasoning and task execution -- is revolutionizing the way organizations operate.

The search for effective collaboration between humans and computer systems is one of the biggest challenges in Artificial Intelligence. One of the more effective mechanisms that humans use to coordinate with one another is theory of mind (ToM). ToM can be described as the ability to `take someone else's perspective and make estimations of their beliefs, desires and intentions, in order to make sense of their behaviour and attitudes towards the world'. If leveraged properly, this skill can be very useful in Human-AI collaboration. This introduces the question how we implement ToM when building an AI system. Humans and AI Systems work quite differently, and ToM is a multifaceted concept, each facet rooted in different research traditions across the cognitive and developmental sciences. We observe that researchers from artificial intelligence and the computing sciences, ourselves included, often have difficulties finding their way in the ToM literature. In this paper, we identify four common misconceptions around ToM that we believe should be taken into account when developing an AI system. We have hyperbolised these misconceptions for the sake of the argument, but add nuance in their discussion. The misconceptions we discuss are: (1) "Humans Use a ToM Module, So AI Systems Should As Well". (2) "Every Social Interaction Requires (Advanced) ToM". (3) "All ToM is the Same". (4) "Current Systems Already Have ToM". After discussing the misconception, we end each section by providing tentative guidelines on how the misconception can be overcome.

Inspired by human cognition, metacognition has gained significant attention for its potential to enhance autonomy, adaptability, and robust learning in artificial agents. Yet research on Computational Metacognitive Architectures (CMAs) remains fragmented: diverse theories, terminologies, and design choices have led to disjointed developments and limited comparability across systems. Existing overviews and surveys often remain at a broad, conceptual level, making it difficult to synthesize deeper insights into the underlying algorithms and representations, and their respective success. We address this gap by performing an explorative systematic review of how CMAs model, store, remember and process their metacognitive experiences, one of Flavell's (1979) three foundational components of metacognition. Following this organizing principle, we identify 35 CMAs that feature episodic introspective data ranging from symbolic event traces to sub-symbolic arousal metrics. We consider different aspects - ranging from the underlying psychological theories to the content and structure of collected data, to the algorithms used and evaluation results - and derive a unifying perspective that allows us to compare in depth how different Computational Metacognitive Architectures (CMAs) leverage metacognitive experiences for tasks such as error diagnosis, self-repair, and goal-driven learning. Our findings highlight both the promise of metacognitive experiences - in boosting adaptability, explainability, and overall system performance - and the persistent lack of shared standards or evaluation benchmarks.

Feasible Force Set Shaping for a Payload-Carrying Platform Consisting of Tiltable Multiple UA Vs Connected Via Passive Hinge Joints Takumi Ito 1, Hayato Kawashima 1, Riku Funada 1, and Mitsuji Sampei 1 Abstract -- This paper presents a method for shaping the feasible force set of a payload-carrying platform composed of multiple Unmanned Aerial V ehicles (UA Vs) and proposes a control law that leverages the advantages of this shaped force set. The UA Vs are connected to the payload through passively rotatable hinge joints. The joint angles are controlled by the differential thrust produced by the rotors, while the total force generated by all the rotors is responsible for controlling the payload. The shape of the set of the total force depends on the tilt angles of the UA Vs, which allows us to shape the feasible force set by adjusting these tilt angles. This paper aims to ensure that the feasible force set encompasses the required shape, enabling the platform to generate force redundantly--meaning in various directions. We then propose a control law that takes advantage of this redundancy. I. INTRODUCTION The advancement of Unmanned Aerial V ehicles (UA Vs) has enabled applications to be conducted automatically, such as agriculture [1], environmental monitoring [2], and inspection [3]. Additionally, there is potential for using UA Vs in payload transportation [4] due to increased package supplies and a labor shortage. Despite these diverse applications, conventional UA Vs, consisting of multiple rotors pointing upward and placed on the same plane, are known as an un-deractuated system at SE(3) space (six-dimensional space).

Despite the growing interest in collaborative AI, designing systems that seamlessly integrate human input remains a major challenge. In this study, we developed a task to systematically examine human preferences for collaborative agents. We created and evaluated five collaborative AI agents with strategies that differ in the manner and degree they adapt to human actions. Participants interacted with a subset of these agents, evaluated their perceived traits, and selected their preferred agent. We used a Bayesian model to understand how agents' strategies influence the Human-AI team performance, AI's perceived traits, and the factors shaping human-preferences in pairwise agent comparisons. Our results show that agents who are more considerate of human actions are preferred over purely performance-maximizing agents. Moreover, we show that such human-centric design can improve the likability of AI collaborators without reducing performance. We find evidence for inequality-aversion effects being a driver of human choices, suggesting that people prefer collaborative agents which allow them to meaningfully contribute to the team. Taken together, these findings demonstrate how collaboration with AI can benefit from development efforts which include both subjective and objective metrics.

The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current development of agentic AI requires a more holistic, systems-theoretic perspective in order to fully understand their capabilities and mitigate any emergent risks. The primary motivation for our position is that AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation in the true capabilities and associated risks of agentic AI. We describe some fundamental mechanisms by which advanced capabilities can emerge from (comparably simpler) agents simply due to their interaction with the environment and other agents. Informed by an extensive amount of existing literature from various fields, we outline mechanisms for enhanced agent cognition, emergent causal reasoning ability, and metacognitive awareness. We conclude by presenting some key open challenges and guidance for the development of agentic AI. We emphasize that a systems-level perspective is essential for better understanding, and purposefully shaping, agentic AI systems.

In recent years, online lecture videos have become an increasingly popular resource for acquiring new knowledge. Systems capable of effectively understanding/indexing lecture videos are thus highly desirable, enabling downstream tasks like question answering to help users efficiently locate specific information within videos. This work proposes PreMind, a novel multi-agent multimodal framework that leverages various large models for advanced understanding/indexing of presentation-style videos. PreMind first segments videos into slide-presentation segments using a Vision-Language Model (VLM) to enhance modern shot-detection techniques. Each segment is then analyzed to generate multimodal indexes through three key steps: (1) extracting slide visual content, (2) transcribing speech narratives, and (3) consolidating these visual and speech contents into an integrated understanding. Three innovative mechanisms are also proposed to improve performance: leveraging prior lecture knowledge to refine visual understanding, detecting/correcting speech transcription errors using a VLM, and utilizing a critic agent for dynamic iterative self-reflection in vision analysis. Compared to traditional video indexing methods, PreMind captures rich, reliable multimodal information, allowing users to search for details like abbreviations shown only on slides. Systematic evaluations on the public LPM dataset and an internal enterprise dataset are conducted to validate PreMind's effectiveness, supported by detailed analyses.

--Social media has become integral to minors' daily lives and is used for various purposes, such as making friends, exploring shared interests, and engaging in educational activities. However, the increase in screen time has also led to heightened challenges, including cyberbullying, online grooming, and exploitations posed by malicious actors. Traditional content moderation techniques have proven ineffective against exploiters' evolving tactics. T o address these growing challenges, we propose the EdgeAIGuard content moderation approach that is designed to protect minors from online grooming and various forms of digital exploitation. The proposed method comprises a multi-agent architecture deployed strategically at the network edge to enable rapid detection with low latency and prevent harmful content targeting minors. The experimental results show the proposed method is significantly more effective than the existing approaches. Social media platforms have fundamentally transformed how individuals communicate, connect, and share information. It is not an exaggeration to say that social media has become integral to our daily lives. For minors, these platforms serve to form their identities, express themselves, and interact socially [1]. A recent study revealed that approximately 84% of teenagers aged 13 to 17 actively use social media for an average of 4.8 hours daily [2]. Platforms like Snapchat, TikTok, and Instagram are easily accessible on devices like smartphones and wearables, allowing users to share their personal experiences while engaging with diverse content.