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.

As foundation models are increasingly deployed as interacting agents in multi-agent systems, their collective behavior raises new challenges for trustworthiness, transparency, and accountability. Traditional coordination mechanisms, such as centralized oversight or adversarial adjudication, struggle to scale and often obscure how decisions emerge. We introduce a market-making framework for multi-agent large language model (LLM) coordination that organizes agent interactions as structured economic exchanges. In this setup, each agent acts as a market participant, updating and trading probabilistic beliefs, to converge toward shared, truthful outcomes. By aligning local incentives with collective epistemic goals, the framework promotes self-organizing, verifiable reasoning without requiring external enforcement. Empirically, we evaluate this approach across factual reasoning, ethical judgment, and commonsense inference tasks. Market-based coordination yields accuracy gains of up to 10% over single-shot baselines while preserving interpretability and transparency of intermediate reasoning steps. Beyond these improvements, our findings demonstrate that economic coordination principles can operationalize accountability and robustness in multi-agent LLM systems, offering a scalable pathway toward self-correcting, socially responsible AI capable of maintaining trust and oversight in real world deployment scenarios.

Synthetic data has become essential for training foundation models, yet benchmark contamination threatens evaluation integrity. Although existing detection methods identify token-level overlap, they fail to detect semantic-level contamination where synthetic data conceptually resemble benchmarks without lexical overlap. This gap is critical as foundation models increasingly train on synthetic data that may implicitly encode benchmark knowledge. We propose a hierarchical contamination detection framework operating at four levels: token level, semantic level, reasoning pattern, and performance cliff detection. Through controlled experiments on MMLU, GSM8K and HumanEval, we demonstrate that semantic-level contamination evades existing methods (F1=0.17-0.49) but is effectively detected by our hierarchical approach (F1 = 0.76), with an average improvement of 26. 5\% over state-of-the-art baselines. Our framework provides practitioners with practical tools for audit pipelines and enables responsible deployment of synthetic training data.

Training Large Language Models (LLMs) typically involves a two-stage pipeline at the output layer: hidden states are projected into vocabulary logits via a linear transformation (lm_head), followed by cross-entropy loss computation against target tokens. While conceptually simple, this design incurs substantial overhead. The intermediate logits tensor, with dimensions proportional to batch size, sequence length, and vocabulary size, must be fully materialized in GPU memory, even though only one target token per position is ultimately used. This leads to significant memory footprint and bandwidth comsumption, limiting scalability and slowing training throughput. In this work, we introduce a novel approach to integrates the output projection and loss prediction into a single operation. By directly computing the loss from hidden states and target tokens, our approach bypasses explicit logits materialization. This design reduces memory usage and alleviates bandwidth pressure. Experiments on LLM training demonstrate that our method achieves substantial memory savings and measurable speedups compared to the standard two-stage pipeline, enabling large batch sizes and longer sequences without sacrificing accuracy. Our work highlights the benefits of rethinking the boundary between projection and prediction, offering a practical systems optimization for efficient LLM training.

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, from conversational AI to code generation and content creation [1, 2, 3]. However, the deployment of these models in production environments presents significant engineering challenges. The computational demands of autoregressive text generation, combined with the massive parameter counts of modern LLMs, necessitate specialized serving infrastructure that can efficiently manage GPU resources while meeting application-specific performance requirements. The serving infrastructure for LLMs must address several competing objectives: maximizing throughput to serve many concurrent users, minimizing latency for responsive user experiences, and efficiently utilizing expensive GPU resources. Different applications prioritize these objectives differently--a chatbot requires low latency for individual requests, while a batch document processing system prioritizes throughput. This variation in requirements has led to the development of specialized serving frameworks, each making different design trade-offs. Among the available open-source solutions, vLLM [4] and HuggingFace Text Generation Inference (TGI) [5] have emerged as leading frameworks, widely adopted in both research and production settings.

Recent advances in LLM-guided evolutionary computation, particularly AlphaEvolve (Novikov et al., 2025; Georgiev et al., 2025), have demonstrated remarkable success in discovering novel mathematical constructions and solving challenging optimization problems. However, the high-level descriptions in published work leave many implementation details unspecified, hindering reproducibility and further research. In this report we present GigaEvo, an extensible open-source framework that enables researchers to study and experiment with hybrid LLM-evolution approaches inspired by AlphaEvolve. Our system provides modular implementations of key components: MAP-Elites quality-diversity algorithms, asynchronous DAG-based evaluation pipelines, LLM-driven mutation operators with insight generation and bidirectional lineage tracking, and flexible multi-island evolutionary strategies. In order to assess reproducibility and validate our implementation we evaluate GigaEvo on challenging problems from the AlphaEvolve paper: Heil-bronn triangle placement, circle packing in squares, and high-dimensional kissing numbers. The framework emphasizes modularity, concurrency, and ease of experimentation, enabling rapid prototyping through declarative configuration. We provide detailed descriptions of system architecture, implementation decisions, and experimental methodology to support further research in LLM-driven evolutionary methods. The recent paper (Novikov et al., 2025) introduced AlphaEvolve, a framework that combines large language model (LLM) code generation with evolutionary computation, achieving state-of-the-art results on challenging algorithmic and mathematical problems.

This work introduces Llamazip, a novel lossless text compression algorithm based on the predictive capabilities of the LLaMA3 language model. Llamazip achieves significant data reduction by only storing tokens that the model fails to predict, optimizing storage efficiency without compromising data integrity. Key factors affecting its performance, including quantization and context window size, are analyzed, revealing their impact on compression ratios and computational requirements. Beyond compression, Llamazip demonstrates the potential to identify whether a document was part of the training dataset of a language model. This capability addresses critical concerns about data provenance, intellectual property, and transparency in language model training.

Anomaly detection on attributed graphs plays an essential role in applications such as fraud detection, intrusion monitoring, and misinformation analysis. However, text-attributed graphs (TAGs), in which node information is expressed in natural language, remain underexplored, largely due to the absence of standardized benchmark datasets. In this work, we introduce TAG-AD, a comprehensive benchmark for anomaly node detection on TAGs. TAG-AD leverages large language models (LLMs) to generate realistic anomalous node texts directly in the raw text space, producing anomalies that are semantically coherent yet contextually inconsistent and thus more reflective of real-world irregularities. In addition, TAG-AD incorporates multiple other anomaly types, enabling thorough and reproducible evaluation of graph anomaly detection (GAD) methods. With these datasets, we further benchmark existing unsupervised GNN-based GAD methods as well as zero-shot LLMs for GAD. As part of our zero-shot detection setup, we propose a retrieval-augmented generation (RAG)-assisted, LLM-based zero-shot anomaly detection framework. The framework mitigates reliance on brittle, hand-crafted prompts by constructing a global anomaly knowledge base and distilling it into reusable analysis frameworks. Our experimental results reveal a clear division of strengths: LLMs are particularly effective at detecting contextual anomalies, whereas GNN-based methods remain superior for structural anomaly detection. Moreover, RAG-assisted prompting achieves performance comparable to human-designed prompts while eliminating manual prompt engineering, underscoring the practical value of our RAG-assisted zero-shot LLM anomaly detection framework.

With the rapid advancement of large language models (LLMs), aligning them with human values for safety and ethics has become a critical challenge. This problem is especially challenging when multiple, potentially conflicting human values must be considered and balanced. Although several variants of existing alignment methods (such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO)) have been proposed to address multi-value alignment, they suffer from notable limitations: 1) they are often unstable and inefficient in multi-value optimization; and 2) they fail to effectively handle value conflicts. As a result, these approaches typically struggle to achieve optimal trade-offs when aligning multiple values. To address this challenge, we propose a novel framework called Multi-V alue Alignment (MV A). It mitigates alignment degradation caused by parameter interference among diverse human values by minimizing their mutual information. Furthermore, we propose a value extrapolation strategy to efficiently explore the Pareto frontier, thereby constructing a set of LLMs with diverse value preferences. Extensive experiments demonstrate that MV A consistently outperforms existing baselines in aligning LLMs with multiple human values.

With the rapid development of deep learning, large language models have shown strong capabilities in complex reasoning tasks such as mathematical equation solving. However, their substantial computational and storage costs hinder practical deployment. This paper proposes a lightweight optimization method that integrates dynamic attention head pruning with knowledge distillation. The approach dynamically evaluates the importance of each attention head in the multi-head attention mechanism using a combination of weight norms and entropy, and prunes redundant heads in real time to reduce computational overhead. To mitigate performance degradation, knowledge distillation transfers information from the original model to the pruned student, enabling the smaller model to preserve reasoning ability. Experiments conducted on both Math23k and ASDiv-A verify the effectiveness of the proposed method. For example, on Math23k with a 30% pruning ratio, parameters are reduced by 18.7%, inference speed is improved by 27.5%, FLOPs are reduced by 19.3%, and accuracy drops only 0.7% (from 84.4% to 83.7%). These results demonstrate that the method achieves substantial efficiency gains while maintaining strong reasoning performance, providing a practical solution for efficient deployment of large language models in mathematical reasoning tasks.