arXiv:2601.16986v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage sequences stored in the Key-Value (KV) cache. Unlike traditional generation tasks where all tokens are uniformly important, CoT emphasizes the final answer, rendering conventional KV compression strategies ineffective. In this paper, we present Crystal-KV, an efficient KV cache management framework tailored for CoT reasoning. Our key insight is the […]

Ver mais

arXiv:2601.08950v1 Announce Type: new Abstract: In educational applications, LLMs exhibit several fundamental pedagogical limitations, such as their tendency to reveal solutions rather than support dialogic learning. We introduce ConvoLearn (https://huggingface.co/datasets/masharma/convolearn ), a dataset grounded in knowledge building theory that operationalizes six core pedagogical dimensions: cognitive engagement, formative assessment, accountability, cultural responsiveness, metacognition, and power dynamics. We construct a semi-synthetic dataset of 1250 tutor-student dialogues (20 turns each) in middle school Earth Science through controlled interactions between human teachers […]

Ver mais

arXiv:2602.20332v1 Announce Type: new Abstract: Advanced reasoning capabilities in Large Language Models (LLMs) have led to more frequent hallucinations; yet most mitigation work focuses on open-source models for post-hoc detection and parameter editing. The dearth of studies focusing on hallucinations in closed-source models is especially concerning, as they constitute the vast majority of models in institutional deployments. We introduce QueryBandits, a model-agnostic contextual bandit framework that adaptively learns online to select the optimal query-rewrite strategy by leveraging an […]

Ver mais

Victoria, Seychelles, February 5, 2026 MEXC, the world’s fastest-growing digital asset exchange and a pioneer of true zero-fee trading, announced the official launch of the Commodity Zero-Fee Gala. It offers zero-fee trading on commodity assets including gold and silver, high-yield staking opportunities, and $1 million in trading rewards. Amid recent activity in global commodity markets, particularly in gold and silver, traders’ demand for diversified assets and strategies is rising. MEXC is expanding user access to tokenized gold, silver, […]

Ver mais

arXiv:2602.15977v1 Announce Type: new Abstract: An algorithm on weighted graphs is called universally optimal if it is optimal for every input graph, in the worst case taken over all weight assignments. Informally, this means the algorithm is competitive even with algorithms that are optimized for only one specific input graph. Universal optimality was recently introduced [Haeupler et al. 2024] as an alternative to the stronger, but often unachievable instance optimality. In this paper, we extend the concept of […]

Ver mais

Most current approaches to agent reliability involve mixing validation logic (regex checks, JSON parsing, retries) directly with application logic (prompts/tools). This usually results in decorators on every function or heavy try/except blocks inside the agent loop. I’ve been experimenting with an alternative architecture: an Agent Service Mesh. Instead of decorating individual functions, this approach involves monkeypatching the agent framework (e.g., PydanticAI or OpenAI SDK) at the entry point. The “Mesh” uses introspection to detect which tools or output […]

Ver mais

arXiv:2601.15325v1 Announce Type: new Abstract: Dynamic community detection plays a crucial role in understanding the temporal evolution of community structures in complex networks. Existing methods based on nonnegative tensor RESCAL decomposition typically require the decomposition rank to equal the number of communities, which limits model flexibility. This paper proposes an improved MLP-enhanced nonnegative tensor decomposition model (MLP-NTD) that incorporates a multilayer perceptron (MLP) after RESCAL decomposition for community mapping, thereby decoupling the decomposition rank from the number of […]

Ver mais

In modern applications such as ECG monitoring, neuroimaging, wearable sensing, and industrial equipment diagnostics, complex and continuously structured data are ubiquitous, presenting both challenges and opportunities for functional data analysis. However, existing methods face a critical trade-off: conventional functional models are limited by linearity, whereas deep learning approaches lack interpretable region selection for sparse effects. To bridge these gaps, we propose a sparse Bayesian functional deep neural network (sBayFDNN). It learns adaptive functional embeddings through a deep Bayesian […]

Ver mais

arXiv:2501.10471v2 Announce Type: replace-cross Abstract: Clustering large high-dimensional datasets with diverse variable is essential for extracting high-level latent information from these datasets. Here, we developed an unsupervised clustering algorithm, we call “Village-Net”. Village-Net is specifically designed to effectively cluster high-dimension data without priori knowledge on the number of existing clusters. The algorithm operates in two phases: first, utilizing K-Means clustering, it divides the dataset into distinct subsets we refer to as “villages”. Next, a weighted network is created, […]

Ver mais