Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after deployment, limiting their ability to adapt to dynamic and evolving environments. To this end, recent research has explored agent evolution techniques that aim to automatically enhance agent systems based on interaction data and environmental feedback. This emerging direction lays the foundation for self-evolving AI agents, which bridge the static capabilities of foundation models with the continuous adaptability required by lifelong agentic systems. In this survey, we provide a comprehensive review of existing techniques for self-evolving agentic systems. Specifically, we first introduce a unified conceptual framework that abstracts the feedback loop underlying the design of self-evolving agentic systems. The framework highlights four key components: System Inputs, Agent System, Environment, and Optimisers, serving as a foundation for understanding and comparing different strategies. Based on this framework, we systematically review a wide range of self-evolving techniques that target different components of the agent system. We also investigate domain-specific evolution strategies developed for specialised fields such as biomedicine, programming, and finance, where optimisation objectives are tightly coupled with domain constraints. In addition, we provide a dedicated discussion on the evaluation, safety, and ethical considerations for self-evolving agentic systems, which are critical to ensuring their effectiveness and reliability. This survey aims to provide researchers and practitioners with a systematic understanding of self-evolving AI agents, laying the foundation for the development of more adaptive, autonomous, and lifelong agentic systems.

Abstract-- The interaction between humans and AI in safety-critical systems presents a unique set of challenges that re main partially addressed by existing frameworks. These challen ges stem from the complex interplay of requirements for transparency, trust, and explainability, coupled with the neces sity for robust and safe decision-making. A framework that holistic ally integrates human and AI capabilities while addressing thes e concerns is notably required, bridging the critical gaps in designing, deploying, and maintaining safe and effective sys tems. This paper proposes a holistic conceptual framework for cri tical infrastructures by adopting an interdisciplinary approac h. It integrates traditionally distinct fields such as mathemati cs, decision theory, computer science, philosophy, psycholog y, and cognitive engineering and draws on specialized engineerin g domains, particularly energy, mobility, and aeronautics. Its flexibility is further demonstrated through a case study on power grid management. Artificial Intelligence (AI) is showing high potential to transform the management of critical infrastructures [1], tackling pressing challenges like climate change and the rising demand for energy and mobility systems while advancing strategic objectives such as energy transition and digi tal transformation. On the other hand, integrating AI in critic al sectors introduces significant challenges, many of which ar e already being addressed by emerging regulatory frameworks, such as the European Union AI Act. These frameworks emphasize the importance of safety, transparency, and adhe r-ence to ethical standards and principles to mitigate a wide range of risks, including technical, social, and environme ntal hazards associated with deploying AI in high-risk domains. Another key challenge lies in fostering effective human-AI collaboration.

The role of Artificial Intelligence (AI) in education is undergoing a rapid transformation, moving beyond its historical function as an instructional tool towards a new potential as an active participant in the learning process. This shift is driven by the emergence of agentic AI, autonomous systems capable of proactive, goal-directed action. However, the field lacks a robust conceptual framework to understand, design, and evaluate this new paradigm of human-AI interaction in learning. This paper addresses this gap by proposing a novel conceptual framework (the APCP framework) that charts the transition from AI as a tool to AI as a collaborative partner. We present a four-level model of escalating AI agency within human-AI collaborative learning: (1) the AI as an Adaptive Instrument, (2) the AI as a Proactive Assistant, (3) the AI as a Co-Learner, and (4) the AI as a Peer Collaborator. Grounded in sociocultural theories of learning and Computer-Supported Collaborative Learning (CSCL), this framework provides a structured vocabulary for analysing the shifting roles and responsibilities between human and AI agents. The paper further engages in a critical discussion of the philosophical underpinnings of collaboration, examining whether an AI, lacking genuine consciousness or shared intentionality, can be considered a true collaborator. We conclude that while AI may not achieve authentic phenomenological partnership, it can be designed as a highly effective functional collaborator. This distinction has significant implications for pedagogy, instructional design, and the future research agenda for AI in education, urging a shift in focus towards creating learning environments that harness the complementary strengths of both human and AI. For decades, the integration of Artificial Intelligence in Education (AIED) has been a subject of intense research and development, promising to transform teaching and learning (Yan, Greiff, Teuber and Gašević, 2024; Giannakos, Azevedo, Brusilovsky, Cukurova, Dimitriadis, Hernandez-Leo, Järvelä, Mavrikis and Rienties, 2025; Chen, Zou, Xie, Cheng and Liu, 2022). Historically, this promise has been pursued primarily through the lens of individualization and efficiency. The predominant applications of AIED have been Intelligent Tutoring Systems (ITS) and adaptive learning platforms, which leverage AI to provide personalized instruction, real-time feedback, and customized learning pathways (Ouyang and Jiao, 2021; Kulik and Fletcher, 2016). These systems, often built on cognitive and mastery-learning principles, have demonstrated effectiveness in specific, well-defined domains (Kulik and Fletcher, 2016). However, they have also faced criticism for frequently replicating traditional, teacher-centric pedagogical models, where knowledge is transmitted to a passive learner (Ouyang and Jiao, 2021; Kulik and Fletcher, 2016).

We identify a second machine turn in the process of mathematical discovery: after automating proof-checking, AI is now poised to automate the *creation* of mathematical concepts themselves. We discuss the current state of the art, obstacles and potential solutions as well as a preliminary attempt at mathematizing the creation of concepts itself. The paper ends with an assessment of how these capabilities could reshape mathematics and human-machine collaboration, and a few different futures we might find ourselves in.

Collective Adaptive Intelligence (CAI) represent a transformative approach in embodied AI, wherein numerous autonomous agents collaborate, adapt, and self-organize to navigate complex, dynamic environments. By enabling systems to reconfigure themselves in response to unforeseen challenges, CAI facilitate robust performance in real-world scenarios. This article introduces a conceptual framework for designing and analyzing CAI. It delineates key attributes including task generalization, resilience, scalability, and self-assembly, aiming to bridge theoretical foundations with practical methodologies for engineering adaptive, emergent intelligence. By providing a structured foundation for understanding and implementing CAI, this work seeks to guide researchers and practitioners in developing more resilient, scalable, and adaptable AI systems across various domains.

Tariff exemptions are fundamental to attracting Foreign Direct Investment (FDI) into the manufacturing sector, though the associated administrative processes present areas for optimization for both investing entities and the national tax authority. This paper proposes a conceptual framework to empower tax administration by leveraging a synergistic integration of Optical Character Recognition (OCR) and Large Language Model (LLM) technologies. The proposed system is designed to first utilize OCR for intelligent digitization, precisely extracting data from diverse application documents and key regulatory texts such as tariff orders. Subsequently, the LLM would enhance the capabilities of administrative officers by automating the critical and time-intensive task of verifying submitted HS Tariff Codes for machinery, equipment, and raw materials against official exemption lists. By enhancing the speed and precision of these initial assessments, this AI-driven approach systematically reduces potential for non-alignment and non-optimized exemption utilization, thereby streamlining the investment journey for FDI companies. For the national administration, the benefits include a significant boost in operational capacity, reduced administrative load, and a strengthened control environment, ultimately improving the ease of doing business and solidifying the nation's appeal as a premier destination for high-value manufacturing FDI.

It has been hypothesized that neural networks with similar architectures trained on similar data learn shared representations relevant to the learning task. We build on this idea by extending the conceptual framework where representations learned across models trained on the same data can be expressed as linear combinations of a \emph{universal} set of basis features. These basis features underlie the learning task itself and remain consistent across models, regardless of scale. From this framework, we propose the \textbf{Linear Representation Transferability (LRT)} Hypothesis -- that there exists an affine transformation between the representation spaces of different models. To test this hypothesis, we learn affine mappings between the hidden states of models of different sizes and evaluate whether steering vectors -- directions in hidden state space associated with specific model behaviors -- retain their semantic effect when transferred from small to large language models using the learned mappings. We find strong empirical evidence that such affine mappings can preserve steering behaviors. These findings suggest that representations learned by small models can be used to guide the behavior of large models, and that the LRT hypothesis may be a promising direction on understanding representation alignment across model scales.

In machine learning (ML) applications, unfairness is triggered due to bias in the data, the data curation process, erroneous assumptions, and implicit bias rendered during the development process. It is also well-accepted by researchers that fairness in ML application development is highly subjective, with a lack of clarity of what it means from an ML development and implementation perspective. Thus, in this research, we investigate and formalize the notion of the perceived fairness of ML development from a sociotechnical lens. Our goal in this research is to understand the characteristics of perceived fairness in ML applications. We address this research goal using a three-pronged strategy: 1) conducting virtual focus groups with ML developers, 2) reviewing existing literature on fairness in ML, and 3) incorporating aspects of justice theory relating to procedural and distributive justice. Based on our theoretical exposition, we propose operational attributes of perceived fairness to be transparency, accountability, and representativeness. These are described in terms of multiple concepts that comprise each dimension of perceived fairness. We use this operationalization to empirically validate the notion of perceived fairness of machine learning (ML) applications from both the ML practioners and users perspectives. The multidimensional framework for perceived fairness offers a comprehensive understanding of perceived fairness, which can guide the creation of fair ML systems with positive implications for society and businesses.

Automated Vehicles (AVs) hold promise for revolutionizing transportation by improving road safety, traffic efficiency, and overall mobility. Despite the steady advancement in high-level AVs in recent years, the transition to full automation entails a period of mixed traffic, where AVs of varying automation levels coexist with human-driven vehicles (HDVs). Making AVs socially compliant and understood by human drivers is expected to improve the safety and efficiency of mixed traffic. Thus, ensuring AVs compatibility with HDVs and social acceptance is crucial for their successful and seamless integration into mixed traffic. However, research in this critical area of developing Socially Compliant AVs (SCAVs) remains sparse. This study carries out the first comprehensive scoping review to assess the current state of the art in developing SCAVs, identifying key concepts, methodological approaches, and research gaps. An expert interview was also conducted to identify critical research gaps and expectations towards SCAVs. Based on the scoping review and expert interview input, a conceptual framework is proposed for the development of SCAVs. The conceptual framework is evaluated using an online survey targeting researchers, technicians, policymakers, and other relevant professionals worldwide. The survey results provide valuable validation and insights, affirming the significance of the proposed conceptual framework in tackling the challenges of integrating AVs into mixed-traffic environments. Additionally, future research perspectives and suggestions are discussed, contributing to the research and development agenda of SCAVs.

Reinforcement Learning from Human feedback (RLHF) has become a powerful tool to fine-tune or train agentic machine learning models. Similar to how humans interact in social contexts, we can use many types of feedback to communicate our preferences, intentions, and knowledge to an RL agent. However, applications of human feedback in RL are often limited in scope and disregard human factors. In this work, we bridge the gap between machine learning and human-computer interaction efforts by developing a shared understanding of human feedback in interactive learning scenarios. We first introduce a taxonomy of feedback types for reward-based learning from human feedback based on nine key dimensions. Our taxonomy allows for unifying human-centered, interface-centered, and model-centered aspects. In addition, we identify seven quality metrics of human feedback influencing both the human ability to express feedback and the agent's ability to learn from the feedback. Based on the feedback taxonomy and quality criteria, we derive requirements and design choices for systems learning from human feedback. We relate these requirements and design choices to existing work in interactive machine learning. In the process, we identify gaps in existing work and future research opportunities. We call for interdisciplinary collaboration to harness the full potential of reinforcement learning with data-driven co-adaptive modeling and varied interaction mechanics.