The Token Games: Evaluating Language Model Reasoning with Puzzle Duels
arXiv:2602.17831v1 Announce Type: new
Abstract: Evaluating the reasoning capabilities of Large Language Models is increasingly challenging as models improve. Human curation of hard questions is highly expensive, especially in recent benchmarks using PhD-level domain knowledge to challenge the most ...
El Agente Gr\'afico: Structured Execution Graphs for Scientific Agents
arXiv:2602.17902v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used to automate scientific workflows, yet their integration with heterogeneous computational tools remains ad hoc and fragile. Current agentic approaches often rely on unstructured text to manage context ...
Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems
arXiv:2602.17910v1 Announce Type: new
Abstract: Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End Modulation for...
The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost but rely on heuristics, such as recency or past attention scores, which serve o...
Quantum computer breakthrough tracks qubit fluctuations in real time
Qubits, the heart of quantum computers, can change performance in fractions of a second — but until now, scientists couldn’t see it happening. Researchers at NBI have built a real-time monitoring system that tracks these rapid fluctuations about 100 times faster than previous methods. Using fast FPG...
Apple is (no so quietly) anchoring a vibrant ecosystem of talent, startups, and human-centered innovation. Here’s how its expansion is shaping the next chapter of AI in Austin, Texas.
A Few-Shot LLM Framework for Extreme Day Classification in Electricity Markets
arXiv:2602.16735v1 Announce Type: new
Abstract: This paper proposes a few-shot classification framework based on Large Language Models (LLMs) to predict whether the next day will have spikes in real-time electricity prices. The approach aggregates system state information, including electricity dem...
Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
arXiv:2602.16740v1 Announce Type: new
Abstract: In mechanistic interpretability, recent work scrutinizes transformer "circuits" - sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid-tested for their stability acr...
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
arXiv:2602.16742v1 Announce Type: new
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). However, existing datasets are predominantly derived from either small-scal...
Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems
arXiv:2602.16715v1 Announce Type: new
Abstract: We explore the potential of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Graph-based RAG (GraphRAG) for generating Design Structure Matrices (DSMs). We test these methods on two distinct use cases -- a power screwdriver and ...
Contextuality from Single-State Representations: An Information-Theoretic Principle for Adaptive Intelligence
arXiv:2602.16716v1 Announce Type: new
Abstract: Adaptive systems often operate across multiple contexts while reusing a fixed internal state space due to constraints on memory, representation, or physical resources. Such single-state reuse is ubiquitous in natural and artificial intelligence, yet i...
Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation
arXiv:2602.16727v1 Announce Type: new
Abstract: Large-scale human mobility simulation is critical for applications such as urban planning, epidemiology, and transportation analysis. Recent works treat large language models (LLMs) as human agents to simulate realistic mobility behaviors using struct...
A Koopman-Bayesian Framework for High-Fidelity, Perceptually Optimized Haptic Surgical Simulation
arXiv:2602.15834v1 Announce Type: new
Abstract: We introduce a unified framework that combines nonlinear dynamics, perceptual psychophysics and high frequency haptic rendering to enhance realism in surgical simulation. The interaction of the surgical device with soft tissue is elevated to an augmen...
Memes-as-Replies: Can Models Select Humorous Manga Panel Responses?
arXiv:2602.15842v1 Announce Type: new
Abstract: Memes are a popular element of modern web communication, used not only as static artifacts but also as interactive replies within conversations. While computational research has focused on analyzing the intrinsic properties of memes, the dynamic and c...
Kalman-Inspired Runtime Stability and Recovery in Hybrid Reasoning Systems
arXiv:2602.15855v1 Announce Type: new
Abstract: Hybrid reasoning systems that combine learned components with model-based inference are increasingly deployed in tool-augmented decision loops, yet their runtime behavior under partial observability and sustained evidence mismatch remains poorly under...
arXiv:2602.15877v1 Announce Type: new
Abstract: Generalized Additive Models (GAMs) balance predictive accuracy and interpretability, but manually configuring their structure is challenging. We propose using the multi-objective genetic algorithm NSGA-II to automatically optimize GAMs, jointly minimi...
IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentation
arXiv:2602.15878v1 Announce Type: new
Abstract: In industrial scenarios, data augmentation is an effective approach to improve model performance. However, its benefits are not unidirectionally beneficial. There is no theoretical research or established estimation for the optimal sample size (OSS) i...
Optimization Instability in Autonomous Agentic Workflows for Clinical Symptom Detection
arXiv:2602.16037v1 Announce Type: new
Abstract: Autonomous agentic workflows that iteratively refine their own behavior hold considerable promise, yet their failure modes remain poorly characterized. We investigate optimization instability, a phenomenon in which continued autonomous improvement par...
How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment
arXiv:2602.16039v1 Announce Type: new
Abstract: The rapid rise of large language models (LLMs) is reshaping the landscape of automatic assessment in education. While these systems demonstrate substantial advantages in adaptability to diverse question types and flexibility in output formats, they al...
Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination
arXiv:2602.16050v1 Announce Type: new
Abstract: Background: Large language models have demonstrated strong performance on general medical examinations, but subspecialty clinical reasoning remains challenging due to rapidly evolving guidelines and nuanced evidence hierarchies. Methods: We evaluated ...
Improving Interactive In-Context Learning from Natural Language Feedback
arXiv:2602.16066v1 Announce Type: new
Abstract: Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large language model training paradigm relies heavily on modeling vast, static corp...
Near-Optimal Sample Complexity for Online Constrained MDPs
arXiv:2602.15076v1 Announce Type: new
Abstract: Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used to enforce...
Hybrid Feature Learning with Time Series Embeddings for Equipment Anomaly Prediction
arXiv:2602.15089v1 Announce Type: new
Abstract: In predictive maintenance of equipment, deep learning-based time series anomaly detection has garnered significant attention; however, pure deep learning approaches often fail to achieve sufficient accuracy on real-world data. This study proposes a hy...