API calls by large language models (LLMs) offer a cutting-edge approach for data analysis. However, their ability to effectively utilize tools via API calls remains underexplored in knowledge-intensive domains like meteorology. This paper introduces KG2data, a system that integrates knowledge graphs, LLMs, ReAct agents, and tool-use technologies to enable intelligent data acquisition and query handling in the meteorological field. Using a virtual API, we evaluate API call accuracy across three metrics: name recognition failure, hallucination failure, and call correctness. KG2data achieves superior performance (1.43%, 0%, 88.57%) compared to RAG2data (16%, 10%, 72.14%) and chat2data (7.14%, 8.57%, 71.43%). KG2data differs from typical LLM-based systems by addressing their limited access to domain-specific knowledge, which hampers performance on complex or terminology-rich queries. By using a knowledge graph as persistent memory, our system enhances content retrieval, complex query handling, domain-specific reasoning, semantic relationship resolution, and heterogeneous data integration. It also mitigates the high cost of fine-tuning LLMs, making the system more adaptable to evolving domain knowledge and API structures. In summary, KG2data provides a novel solution for intelligent, knowledge-based question answering and data analysis in domains with high knowledge demands.

Protecting cyberspace requires not only advanced tools but also a shift in how we reason about threats, trust, and autonomy. Traditional cybersecurity methods rely on manual responses and brittle heuristics. To build proactive and intelligent defense systems, we need integrated theoretical frameworks and software tools. Game theory provides a rigorous foundation for modeling adversarial behavior, designing strategic defenses, and enabling trust in autonomous systems. Meanwhile, software tools process cyber data, visualize attack surfaces, verify compliance, and suggest mitigations. Yet a disconnect remains between theory and practical implementation. The rise of Large Language Models (LLMs) and agentic AI offers a new path to bridge this gap. LLM-powered agents can operationalize abstract strategies into real-world decisions. Conversely, game theory can inform the reasoning and coordination of these agents across complex workflows. LLMs also challenge classical game-theoretic assumptions, such as perfect rationality or static payoffs, prompting new models aligned with cognitive and computational realities. This co-evolution promises richer theoretical foundations and novel solution concepts. Agentic AI also reshapes software design: systems must now be modular, adaptive, and trust-aware from the outset. This chapter explores the intersection of game theory, agentic AI, and cybersecurity. We review key game-theoretic frameworks (e.g., static, dynamic, Bayesian, and signaling games) and solution concepts. We then examine how LLM agents can enhance cyber defense and introduce LLM-driven games that embed reasoning into AI agents. Finally, we explore multi-agent workflows and coordination games, outlining how this convergence fosters secure, intelligent, and adaptive cyber systems.

Large Language Models (LLMs) have emerged as a promising paradigm for time series analytics, leveraging their massive parameters and the shared sequential nature of textual and time series data. However, a cross-modality gap exists between time series and textual data, as LLMs are pre-trained on textual corpora and are not inherently optimized for time series. In this tutorial, we provide an up-to-date overview of LLM-based cross-modal time series analytics. We introduce a taxonomy that classifies existing approaches into three groups based on cross-modal modeling strategies, e.g., conversion, alignment, and fusion, and then discuss their applications across a range of downstream tasks. In addition, we summarize several open challenges. This tutorial aims to expand the practical application of LLMs in solving real-world problems in cross-modal time series analytics while balancing effectiveness and efficiency. Participants will gain a thorough understanding of current advancements, methodologies, and future research directions in cross-modal time series analytics.

The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLMs within search routines to iteratively generate and refine candidate algorithms. However, most existing methods rely on off-the-shelf LLMs trained for general coding tasks,leaving a key question open: Do we need LLMs specifically tailored for algorithm design? If so, how can such LLMs be effectively obtained and how well can they generalize across different algorithm design tasks? In this paper, we take a first step toward answering these questions by exploring fine-tuning of LLMs for algorithm design. We introduce a Diversity-Aware Rank based (DAR) sampling strategy to balance training data diversity and quality, then we leverage direct preference optimization to efficiently align LLM outputs with task objectives. Our experiments, conducted on Llama-3.2-1B-Instruct and Llama- 3.1-8B-Instruct, span three distinct algorithm design tasks. Results suggest that finetuned LLMs can significantly outperform their off-the-shelf counterparts with the smaller Llama-3.2-1B-Instruct and match the larger Llama-3.1-8B-Instruct on the admissible set problem. Moreover, we observe promising generalization: LLMs finetuned on specific algorithm design tasks also improve performance on related tasks with varying settings. These findings highlight the value of task-specific adaptation for LLMs in algorithm design and open new avenues for future research.

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance improvements decelerate, which is a phenomenon known as sub-scaling. This paper revisits these scaling laws by examining the impact of data quality and training strategies on model performance. Through extensive empirical analysis of over 400 models, we identify high data density and non-optimal resource allocation as key factors contributing to sub-scaling. High data density leads to diminishing returns due to redundant information, while optimal resource allocation is crucial for sustained performance improvements. We propose a sub-optimal scaling law that better predicts performance in sub-scaling regimes, highlighting the importance of data quality and diversity.

As large language models (LLMs) increasingly power conversational agents, understanding how they model users' emotional states is critical for ethical deployment. Inspired by emotion wheels -- a psychological framework that argues emotions organize hierarchically -- we analyze probabilistic dependencies between emotional states in model outputs. We find that LLMs naturally form hierarchical emotion trees that align with human psychological models, and larger models develop more complex hierarchies. We also uncover systematic biases in emotion recognition across socioeconomic personas, with compounding misclassifications for intersectional, underrepresented groups. Human studies reveal striking parallels, suggesting that LLMs internalize aspects of social perception. Beyond highlighting emergent emotional reasoning in LLMs, our results hint at the potential of using cognitively-grounded theories for developing better model evaluations.

Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence of sensitive, personally identifiable information, and significant heterogeneity in structure and language. We present a modular toolchain that prepares such text data for embedding-based analysis, relying entirely on open-weight models that run on local hardware, requiring only a workstation-level GPU and supporting privacy-sensitive research. The toolchain employs large language model (LLM) prompting to standardize, summarize, and, when needed, translate texts to English for greater comparability. Anonymization is achieved via LLM-based redaction, supplemented with named entity recognition and rule-based methods to minimize the risk of disclosure. We demonstrate the toolchain on a corpus of 10,842 Swedish court decisions under the Care of Abusers Act (LVM), comprising over 56,000 pages. Each document is processed into an anonymized, standardized summary and transformed into a document-level embedding. Validation, including manual review, automated scanning, and predictive evaluation shows the toolchain effectively removes identifying information while retaining semantic content. As an illustrative application, we train a predictive model using embedding vectors derived from a small set of manually labeled summaries, demonstrating the toolchain's capacity for semi-automated content analysis at scale. By enabling structured, privacy-conscious analysis of sensitive documents, our toolchain opens new possibilities for large-scale research in domains where textual data was previously inaccessible due to privacy and heterogeneity constraints.

This shared task has aimed to assess pedagogical abilities of AI tutors powered by large language models (LLMs), focusing on evaluating the quality of tutor responses aimed at student's mistake remediation within educational dialogues. The task consisted of five tracks designed to automatically evaluate the AI tutor's performance across key dimensions of mistake identification, precise location of the mistake, providing guidance, and feedback actionability, grounded in learning science principles that define good and effective tutor responses, as well as the track focusing on detection of the tutor identity. The task attracted over 50 international teams across all tracks. The submitted models were evaluated against gold-standard human annotations, and the results, while promising, show that there is still significant room for improvement in this domain: the best results for the four pedagogical ability assessment tracks range between macro F1 scores of 58.34 (for providing guidance) and 71.81 (for mistake identification) on three-class problems, with the best F1 score in the tutor identification track reaching 96.98 on a 9-class task. In this paper, we overview the main findings of the shared task, discuss the approaches taken by the teams, and analyze their performance. All resources associated with this task are made publicly available to support future research in this critical domain.

Major progress on language models (LMs) in recent years has largely resulted from moving away from specialized models designed for specific tasks, to general models based on powerful architectures (e.g. the Transformer) that learn everything from raw data. Despite this trend, pre-processing steps such as tokenization remain a barrier to true end-to-end foundation models. We introduce a collection of new techniques that enable a dynamic chunking mechanism which automatically learns content- and context- dependent segmentation strategies learned jointly with the rest of the model. Incorporating this into an explicit hierarchical network (H-Net) allows replacing the (implicitly hierarchical) tokenization-LM-detokenization pipeline with a single model learned fully end-to-end. When compute- and data- matched, an H-Net with one stage of hierarchy operating at the byte level outperforms a strong Transformer language model operating over BPE tokens. Iterating the hierarchy to multiple stages further increases its performance by modeling multiple levels of abstraction, demonstrating significantly better scaling with data and matching the token-based Transformer of twice its size. H-Nets pretrained on English show significantly increased character-level robustness, and qualitatively learn meaningful data-dependent chunking strategies without any heuristics or explicit supervision. Finally, the H-Net's improvement over tokenized pipelines is further increased in languages and modalities with weaker tokenization heuristics, such as Chinese and code, or DNA sequences (nearly 4x improvement in data efficiency over baselines), showing the potential of true end-to-end models that learn and scale better from unprocessed data.

Instruction Tuning has emerged as a pivotal post-training paradigm that enables pre-trained language models to better follow user instructions. Despite its significance, little attention has been given to optimizing the loss function used. A fundamental, yet often overlooked, question is whether the conventional auto-regressive objective - where loss is computed only on response tokens, excluding prompt tokens - is truly optimal for instruction tuning. In this work, we systematically investigate the impact of differentially weighting prompt and response tokens in instruction tuning loss, and propose Weighted Instruction Tuning (WIT) as a better alternative to conventional instruction tuning. Through extensive experiments on five language models of different families and scale, three finetuning datasets of different sizes, and five diverse evaluation benchmarks, we show that the standard instruction tuning loss often yields suboptimal performance and limited robustness to input prompt variations. We find that a low-to-moderate weight for prompt tokens coupled with a moderate-to-high weight for response tokens yields the best-performing models across settings and also serve as better starting points for the subsequent preference alignment training. These findings highlight the need to reconsider instruction tuning loss and offer actionable insights for developing more robust and generalizable models. Our code is open-sourced at https://github.com/kowndinya-renduchintala/WIT.