There is great interest in agentic LLMs, large language models that act as agents. We review the growing body of work in this area and provide a research agenda. Agentic LLMs are LLMs that (1) reason, (2) act, and (3) interact. We organize the literature according to these three categories. The research in the first category focuses on reasoning, reflection, and retrieval, aiming to improve decision making; the second category focuses on action models, robots, and tools, aiming for agents that act as useful assistants; the third category focuses on multi-agent systems, aiming for collaborative task solving and simulating interaction to study emergent social behavior. We find that works mutually benefit from results in other categories: retrieval enables tool use, reflection improves multi-agent collaboration, and reasoning benefits all categories. We discuss applications of agentic LLMs and provide an agenda for further research. Important applications are in medical diagnosis, logistics and financial market analysis. Meanwhile, self-reflective agents playing roles and interacting with one another augment the process of scientific research itself. Further, agentic LLMs may provide a solution for the problem of LLMs running out of training data: inference-time behavior generates new training states, such that LLMs can keep learning without needing ever larger datasets. We note that there is risk associated with LLM assistants taking action in the real world, while agentic LLMs are also likely to benefit society.

A NALYTICALD ISCOVERY OF M ANIFOLD WITH M A-CHINE L EARNING Y afei Shen 1 & Huan-Fei Ma 1, & Ling Y ang 1, 1 School of Mathematical Sciences, Soochow University, Suzhou 215006, China A BSTRACT Understanding low-dimensional structures within high-dimensional data is crucial for visualization, interpretation, and denoising in complex datasets. Despite the advancements in manifold learning techniques, key challenges--such as limited global insight and the lack of interpretable analytical descriptions--remain unresolved. In this work, we introduce a novel framework, GAMLA (Global Analytical Manifold Learning using Auto-encoding). GAMLA employs a two-round training process within an auto-encoding framework to derive both character and complementary representations for the underlying manifold. With the character representation, the manifold is represented by a parametric function which unfold the manifold to provide a global coordinate. While with the complementary representation, an approximate explicit manifold description is developed, offering a global and analytical representation of smooth manifolds underlying high-dimensional datasets. This enables the analytical derivation of geometric properties such as curvature and normal vectors. Moreover, we find the two representations together decompose the whole latent space and can thus characterize the local spatial structure surrounding the manifold, proving particularly effective in anomaly detection and categorization. Through extensive experiments on benchmark datasets and real-world applications, GAMLA demonstrates its ability to achieve computational efficiency and interpretability while providing precise geometric and structural insights. This framework bridges the gap between data-driven manifold learning and analytical geometry, presenting a versatile tool for exploring the intrinsic properties of complex data sets. 1 I NTRODUCTION Discovering low-dimensional structures, particularly their geometric properties, from high-dimensional data clouds enables visualization, denoising, and interpretation of complex datasets (Meil a & Zhang, 2023; Belkin & Niyogi, 2003; van der Maaten & Hinton, 2008; McInnes & Healy, 2018; Luo & Hu, 2020). As a result, the concept of manifold learning has attracted significant attention, leading to numerous breakthroughs over the past two decades.

The behavior of the random feature model in the high-dimensional regression framework has become a popular issue of interest in the machine learning literature}. This model is generally considered for feature vectors $x_i = \Sigma^{1/2} x_i'$, where $x_i'$ is a random vector made of independent and identically distributed (iid) entries, and $\Sigma$ is a positive definite matrix representing the covariance of the features. In this paper, we move beyond {\CB this standard assumption by studying the performances of the random features model in the setting of non-iid feature vectors}. Our approach is related to the analysis of the spectrum of large random matrices through random matrix theory (RMT) {\CB and free probability} results. We turn to the analysis of non-iid data by using the notion of variance profile {\CB which} is {\CB well studied in RMT.} Our main contribution is then the study of the limits of the training and {\CB prediction} risks associated to the ridge estimator in the random features model when its dimensions grow. We provide asymptotic equivalents of these risks that capture the behavior of ridge regression with random features in a {\CB high-dimensional} framework. These asymptotic equivalents, {\CB which prove to be sharp in numerical experiments}, are retrieved by adapting, to our setting, established results from operator-valued free probability theory. Moreover, {\CB for various classes of random feature vectors that have not been considered so far in the literature}, our approach allows to show the appearance of the double descent phenomenon when the ridge regularization parameter is small enough.

According to a recent Digital Education Council survey, as many as 86 percent of university students globally use artificial intelligence to assist with their coursework. It's a staggering statistic that's likely to have far-reaching consequences for years to come. So it's not surprising to see a company like Anthropic announce Claude for Education, an initiative it says will equip universities to "play a key role in actively shaping AI's role in society." At the heart of Claude for Education is a new Learning mode that changes how Anthropic's chatbot interacts with users. With the feature engaged, Claude will attempt to guide students to a solution, rather than providing an answer outright, when asked a question.

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvements, the importance of prompt-data construction has been overlooked. This paper addresses this gap by exploring data-driven bottlenecks in RLHF performance scaling, particularly reward hacking and decreasing response diversity. We introduce a hybrid reward system combining reasoning task verifiers (RTV) and a generative reward model (GenRM) to mitigate reward hacking. We also propose a novel prompt-selection method, Pre-PPO, to maintain response diversity and enhance learning effectiveness. Additionally, we find that prioritizing mathematical and coding tasks early in RLHF training significantly improves performance. Experiments across two model sizes validate our methods' effectiveness and scalability. Results show that RTV is most resistant to reward hacking, followed by GenRM with ground truth, and then GenRM with SFT Best-of-N responses. Our strategies enable rapid capture of subtle task-specific distinctions, leading to substantial improvements in overall RLHF performance. This work highlights the importance of careful data construction and provides practical methods to overcome performance barriers in RLHF.

Data-free Knowledge Distillation (DFKD) is a method that constructs pseudo-samples using a generator without real data, and transfers knowledge from a teacher model to a student by enforcing the student to overcome dimensional differences and learn to mimic the teacher's outputs on these pseudo-samples. In recent years, various studies in the vision domain have made notable advancements in this area. However, the varying topological structures and non-grid nature of graph data render the methods from the vision domain ineffective. Building upon prior research into differentiable methods for graph neural networks, we propose a fast and high-quality data-free knowledge distillation approach in this paper. Without compromising distillation quality, the proposed graph-free KD method (ACGKD) significantly reduces the spatial complexity of pseudo-graphs by leveraging the Binary Concrete distribution to model the graph structure and introducing a spatial complexity tuning parameter. This approach enables efficient gradient computation for the graph structure, thereby accelerating the overall distillation process. Additionally, ACGKD eliminates the dimensional ambiguity between the student and teacher models by increasing the student's dimensions and reusing the teacher's classifier. Moreover, it equips graph knowledge distillation with a CL-based strategy to ensure the student learns graph structures progressively. Extensive experiments demonstrate that ACGKD achieves state-of-the-art performance in distilling knowledge from GNNs without training data.

--Audio-Visual Question Answering (A VQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing A VQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. T o address these challenges, we first introduce a novel dataset, FortisA VQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-A VQA dataset and (2) introducing distribution shifts across questions. The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions. Second, we introduce a robust Multimodal Audio-Visual Epistemic Network (MA VEN) that leverages a multifaceted cycle collaborative debiasing strategy to mitigate bias learning. Experimental results demonstrate that our architecture achieves state-of-the-art performance on FortisA VQA, with a notable improvement of 7.81%. Additionally, our evaluation reveals the limited robustness of existing multimodal QA methods. We also verify the plug-and-play capability of our strategy by integrating it with various baseline models across both datasets. UMANS possess the extraordinary capacity to seam-lessly integrate auditory and visual cues, effectively establishing a cohesive relationship between visual and auditory stimuli [1-3]. Jie Ma, Pinghui Wang, Jing Tao and Zhou Su are with the Ministry of Education of Key Laboratory for Intelligent Networks and Network Security, School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China. Zhitao Gao and Jun Liu are with the Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering, School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China. Qi Chai is with the Information Hub, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, 510000, China. The question in current A VQA datasets is generated by a limited set of predefined templates, which may not be in line with the real-world scenario. Our findings indicate that existing methods such as STG [6] are not robust, which may be attributed to excessive bias learning, such as memorizing statistical regularities between critical question words and answers. It requires the system to learn high-order interaction representations of the concepts encompassed with audio, video, and language modalities. As is known to us [8-10], the high-level reasoning ability of the system mainly relies on large-scale data that does not contain harmful biases or statistical regularities. However, completely avoiding the negative bias in datasets seems challenging [11] due to the inherent skewness in real-world data distributions.

This post contains a list of the AI-related seminars that are scheduled to take place between 1 April and 31 May 2025. All events detailed here are free and open for anyone to attend virtually. Lie-Poisson Neural Networks (LPNets): Data-Based Computing of Hamiltonian Systems Speaker: Vakhtang Poutkaradze (University of Alberta) Organised by: University of Minnesota Zoom registration is here. Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function. Speaker: Anh Nguyen (Carnegie Mellon University) Organised by: Carnegie Mellon University Zoom link is here.

Generative AI has the potential to transform personalization and accessibility of education. However, it raises serious concerns about accuracy and helping students become independent critical thinkers. In this study, we designed a helpful AI "Peer" to help students correct fundamental physics misconceptions related to Newtonian mechanic concepts. In contrast to approaches that seek near-perfect accuracy to create an authoritative AI tutor or teacher, we directly inform students that this AI can answer up to 40% of questions incorrectly. In a randomized controlled trial with 165 students, those who engaged in targeted dialogue with the AI Peer achieved post-test scores that were, on average, 10.5 percentage points higher--with over 20 percentage points higher normalized gain--than a control group that discussed physics history. Qualitative feedback indicated that 91% of the treatment group's AI interactions were rated as helpful. Furthermore, by comparing student performance on pre-and post-test questions about the same concept, along with experts' annotations of the AI interactions, we find initial evidence suggesting the improvement in performance does not depend on the correctness of the AI. With further research, the AI Peer paradigm described here could open new possibilities for how we learn, adapt to, and grow with AI. Students have recently been exposed to the remarkable capabilities of Generative AI (AI) in education (AIED). For example, OpenAI's ChatGPT has been reported to successfully support teaching preparation, assessment design and grading, and student learning (Lo, 2023). Systems like ChatGPT show potential to save time and enhance teaching and learning, including critical and higher-order thinking tasks (Lo, 2023).

Mathematics learning entails mastery of both content knowledge and cognitive processing of knowing, applying, and reasoning with it. Automated math assessment primarily has focused on grading students' exhibition of content knowledge by finding textual evidence, such as specific numbers, formulas, and statements. Recent advancements in problem-solving, image recognition, and reasoning capabilities of large language models (LLMs) show promise for nuanced evaluation of students' cognitive skills. Diagnosing cognitive skills needs to infer students' thinking processes beyond textual evidence, which is an underexplored task in LLM-based automated assessment. In this work, we investigate how state-of-the-art LLMs diagnose students' cognitive skills in mathematics. We constructed MathCog, a novel benchmark dataset comprising 639 student responses to 110 expert-curated middle school math problems, each annotated with detailed teachers' diagnoses based on cognitive skill checklists. Using MathCog, we evaluated 16 closed and open LLMs of varying model sizes and vendors. Our evaluation reveals that even the state-of-the-art LLMs struggle with the task, all F1 scores below 0.5, and tend to exhibit strong false confidence for incorrect cases ($r_s=.617$). We also found that model size positively correlates with the diagnosis performance ($r_s=.771$). Finally, we discuss the implications of these findings, the overconfidence issue, and directions for improving automated cognitive skill diagnosis.