We study cost-aware routing for large language models across diverse and dynamic pools of models. Existing approaches often overlook prompt-specific context, rely on expensive model profiling, assume a fixed set of experts, or use inefficient trial-and-error strategies. We introduce Cost-Spectrum Contrastive Routing (CSCR), a lightweight framework that maps both prompts and models into a shared embedding space to enable fast, cost-sensitive selection. CSCR uses compact, fast-to-compute logit footprints for open-source models and perplexity fingerprints for black-box APIs. A contrastive encoder is trained to favor the cheapest accurate expert within adaptive cost bands. At inference time, routing reduces to a single k-NN lookup via a FAISS index, requiring no retraining when the expert pool changes and enabling microsecond latency. Across multiple benchmarks, CSCR consistently outperforms baselines, improving the accuracy-cost tradeoff by up to 25%, while generalizing robustly to unseen LLMs and out-of-distribution prompts.

As large language models (LLMs) are progressively deployed in various real-world applications, personalization of LLMs has become increasingly important. While various approaches to LLM personalization such as prompt-based and training-based methods have been actively explored, the development of effective decoding-time algorithms remains largely overlooked, despite their demonstrated potential. In this paper, we propose CoPe (Contrasting Personal Preference), a novel decoding-time approach applied after performing parameter-efficient fine-tuning (PEFT) on user-specific data. Our core idea is to leverage reward-guided decoding specifically for personalization by maximizing each user's implicit reward signal. We evaluate CoPe across five open-ended personalized text generation tasks. Our empirical results demonstrate that CoPe achieves strong performance, improving personalization by an average of 10.57% in ROUGE-L, without relying on external reward models or additional training procedures.

Nowadays, formal theorem provers have made monumental progress on high-school and competition-level mathematics, but few of them generalize to more advanced mathematics. In this paper, we present REAL-Prover, a new open-source stepwise theorem prover for Lean 4 to push this boundary. This prover, based on our fine-tuned large language model (REAL-Prover-v1) and integrated with a retrieval system (Leansearch-PS), notably boosts performance on solving college-level mathematics problems. To train REAL-Prover-v1, we developed HERALD-AF, a data extraction pipeline that converts natural language math problems into formal statements, and a new open-source Lean 4 interactive environment (Jixia-interactive) to facilitate synthesis data collection. In our experiments, our prover using only supervised fine-tune achieves competitive results with a 23.7% success rate (Pass@64) on the ProofNet dataset-comparable to state-of-the-art (SOTA) models. To further evaluate our approach, we introduce FATE-M, a new benchmark focused on algebraic problems, where our prover achieves a SOTA success rate of 56.7% (Pass@64).

Large Language Models (LLMs) are commonly pretrained on vast corpora of text without utilizing contextual metadata such as source, quality, or topic, leading to a context-free learning paradigm. While recent studies suggest that adding metadata like URL information as context (i.e., auxiliary inputs not used in the loss calculation) can improve training efficiency and downstream performance, they offer limited understanding of which types of metadata are truly effective and under what conditions. In this work, we conduct a systematic evaluation and find that not all metadata types contribute equally. Only URL context speeds up training, whereas quality scores and topic/format domain information offer no clear benefit. Furthermore, the improved downstream performances of URL conditioning emerge only when longer prompts are used at inference time. In addition, we demonstrate that context-aware pretraining enables more controllable generation than context-free pretraining, in a classifier-free guidance fashion. Although topic and format metadata do not accelerate training, they are effective for steering outputs, offering human-interpretable control over generation.

Large language models offer opportunities to simulate multi-party deliberation, but realistic modeling remains limited by a lack of speaker-attributed data. Transcripts produced via automatic speech recognition (ASR) assign anonymous speaker labels (e.g., Speaker_1), preventing models from capturing consistent human behavior. This work introduces a reproducible pipeline to transform public Zoom recordings into speaker-attributed transcripts with metadata like persona profiles and pragmatic action tags (e.g., [propose_motion]). We release three local government deliberation datasets: Appellate Court hearings, School Board meetings, and Municipal Council sessions. Fine-tuning LLMs to model specific participants using this "action-aware" data produces a 67% reduction in perplexity and nearly doubles classifier-based performance metrics for speaker fidelity and realism. Turing-style human evaluations show our simulations are often indistinguishable from real deliberations, providing a practical and scalable method for complex realistic civic simulations.

Mastering one or more programming languages has historically been the gateway to implementing ideas on a computer. Today, that gateway is widening with advances in large language models (LLMs) and artificial intelligence (AI)-powered coding assistants. What matters is no longer just fluency in traditional programming languages but the ability to think computationally by translating problems into forms that can be solved with computing tools. The capabilities enabled by these AI-augmented tools are rapidly leading to the commoditization of computational thinking, such that anyone who can articulate a problem in natural language can potentially harness computing power via AI. This shift is poised to radically influence how we teach computer science and data science in the United States and around the world. Educators and industry leaders are grappling with how to adapt: What should students learn when the hottest new programming language is English? How do we prepare a generation of computational thinkers who need not code every algorithm manually, but must still think critically, design solutions, and verify AI-augmented results? This paper explores these questions, examining the impact of natural language programming on software development, the emerging distinction between programmers and prompt-crafting problem solvers, the reforms needed in computer science and data science curricula, and the importance of maintaining our fundamental computational science principles in an AI-augmented future. Along the way, we compare approaches and share best practices for embracing this new paradigm in computing education.

In recent times, discussions on social media platforms have increasingly come under scrutiny due to the proliferation of science denial and fake news. Traditional solutions, such as regulatory actions, have been implemented to mitigate the spread of misinformation; however, these measures alone are not sufficient. To complement these efforts, educational approaches are becoming essential in empowering users to critically engage with misinformation. Conversation training, through serious games or personalized methods, has emerged as a promising strategy to help users handle science denial and toxic conversation tactics. This paper suggests an interdisciplinary seminar to explore the suitability of Large Language Models (LLMs) acting as a persona of a science denier to support people in identifying misinformation and improving resilience against toxic interactions. In the seminar, groups of four to five students will develop an AI-based chatbot that enables realistic interactions with science-denial argumentation structures. The task involves planning the setting, integrating a Large Language Model to facilitate natural dialogues, implementing the chatbot using the RASA framework, and evaluating the outcomes in a user study. It is crucial that users understand what they need to do during the interaction, how to conclude it, and how the relevant information is conveyed. The seminar does not aim to develop chatbots for practicing debunking but serves to teach AI technologies and test the feasibility of this idea for future applications. The chatbot seminar is conducted as a hybrid, parallel master's module at the participating educational institutions.

High-performance computing (HPC) and parallel computing increasingly rely on global collaboration among diverse teams, yet traditional computing curricula inadequately prepare students for cross-cultural teamwork essential in modern computational research environments. This paper presents Empa, an AI-powered virtual mentor that integrates intercultural collaboration training into undergraduate computing education. Built using large language models and deployed through a progressive web application, Empa guides students through structured activities covering cultural dimensions, communication styles, and conflict resolution that are critical for effective multicultural teamwork. Our system addresses the growing need for culturally competent HPC professionals by helping computing students develop skills to collaborate effectively in international research teams, contribute to global computational projects, and navigate the cultural complexities inherent in distributed computing environments. Pilot preparation for deployment in computing courses demonstrates the feasibility of AI-mediated intercultural training and provides insights into scalable approaches for developing intercultural collaboration skills essential for HPC workforce development.

Modern artificial intelligence systems depend heavily on large datasets for both training and transferring knowledge between models. Knowledge distillation, transfer learning, and dataset distillation have made such transfers more efficient, yet they remain fundamentally data-driven: a teacher must produce examples, logits, or gradients for a student to learn. In this work, we introduce Model-to-Model Knowledge Transmission (M2KT), a novel paradigm for data-free conceptual transfer between neural networks. M2KT enables models to exchange knowledge packets that encapsulate structured concept embeddings, abstraction graphs, reasoning traces, and provenance metadata. Unlike classical distillation, M2KT operates primarily in concept space rather than example space, and it does not require labeled datasets or teacher-generated outputs during transfer. We formalize the notion of concept manifolds, introduce an inter-model alignment mapping between teacher and student latent spaces, and derive a composite loss that enforces geometric, structural, and reasoning consistency together with explicit safety constraints. We further present algorithmic procedures for teacher-side packet generation and student-side ingestion and verification. Experiments on symbolic reasoning with large language models show that M2KT can achieve approximately 85 to 90 percent of teacher performance while reducing data usage by over 98 percent compared to standard knowledge distillation. This work establishes a theoretical and practical foundation for data-free AI-to-AI knowledge transfer and self-improving model ecosystems.

Personalizing digital applications for health behavior change is a promising route to making them more engaging and effective. This especially holds for approaches that adapt to users and their specific states (e.g., motivation, knowledge, wants) over time. However, developing such approaches requires making many design choices, whose effectiveness is difficult to predict from literature and costly to evaluate in practice. In this work, we explore whether large language models (LLMs) can be used out-of-the-box to generate samples of user interactions that provide useful information for training reinforcement learning models for digital behavior change settings. Using real user data from four large behavior change studies as comparison, we show that LLM-generated samples can be useful in the absence of real data. Comparisons to the samples provided by human raters further show that LLM-generated samples reach the performance of human raters. Additional analyses of different prompting strategies including shorter and longer prompt variants, chain-of-thought prompting, and few-shot prompting show that the relative effectiveness of different strategies depends on both the study and the LLM with also relatively large differences between prompt paraphrases alone. We provide recommendations for how LLM-generated samples can be useful in practice.