AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchCategorical Internalisation of Environmental Groupoids for Generalisable POMDP Solving
arXiv:2609.27745v1 Announce Type: new Abstract: This paper advocates category theory as a practical framework for structuring and improving rein- forcement learning in high-dimensional, partially observable environments.…
- arXiv cs.AIresearchEvaluation of pre-trained models for pedagogical assessment of novel AI-assisted educational questions
arXiv:2609.27749v1 Announce Type: new Abstract: The surge in AI-assisted generation of educational materials has outpaced our capacity to validate their pedagogical quality. Automated evaluation using Bloom Classifier mo…
- arXiv cs.AIresearchReporting Under Pressure: Separating Factual and Tonal Sycophancy in LLM Statistical Analysis
arXiv:2609.27756v1 Announce Type: new Abstract: Large language models are increasingly asked to analyze data and report what the results mean, a task distinct from the belief- or preference-alignment settings studied in…
- arXiv cs.AIresearchAlignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure
arXiv:2609.27763v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on explicit chain-of-thought (CoT) reasoning and large context windows to achieve strong performance on complex tasks, but these features…
- arXiv cs.AIresearchAsk Which, Not How Good: Sizing Benchmarks Scored by an LLM
arXiv:2609.27787v1 Announce Type: new Abstract: Benchmarks scored by an LLM judge routinely adjudicate differences of a tenth of a point, but the resolution of those benchmarks has never been measured. Existing sample-co…
- arXiv cs.AIresearchReachable Global Optimization in AI Systems: How Global Is Global?
arXiv:2609.27855v1 Announce Type: new Abstract: AI systems increasingly claim to optimize prompts, policies, architectures, plans, tool-use trajectories, reasoning traces, and test-time computation. This paper argues tha…
- arXiv cs.AIresearchA hierarchy of faithfulness criteria for knowledge base completion
arXiv:2609.27863v1 Announce Type: new Abstract: Knowledge graph completion is evaluated by ranking observed triples above randomly corrupted ones, which treats every unobserved fact as false. When the object being comple…
- arXiv cs.AIresearchA Resilience Recovery Method for Complex Traffic Network Security Based on Trend Forecasting
arXiv:2609.27903v1 Announce Type: new Abstract: Due to the rapid development of information technology, a huge and complex traffic network has been established across various sectors, including aviation, aerospace, vehic…
- arXiv cs.AIresearchSlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference
arXiv:2609.28064v1 Announce Type: new Abstract: Driving world-action models improve planning by coupling multimodal reasoning with future prediction, but their growing inference cost increasingly conflicts with the real-…
- arXiv cs.AIresearchDiscovery of fully efficient fault indicators along a data-based diagnosis process
arXiv:2609.28087v1 Announce Type: new Abstract: The integration of model-based and data-driven paradigms provides a powerful framework for fault diagnosis by combining the interpretability of analytical redundancy relati…
- arXiv cs.AIresearchLearning the Cost of Reliable Inference
arXiv:2609.28322v2 Announce Type: replace Abstract: Benchmarking and routing platforms increasingly act as intermediaries connecting large language model providers with end-users. However, providers on these platforms ty…
- arXiv cs.AIresearchAn Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice
arXiv:2609.28335v2 Announce Type: replace Abstract: Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static assessments, when supporting evidence is accessible at a…
- arXiv cs.AIresearchStudentBench: AI and human tutoring yield equivalent GRE learning gains
arXiv:2609.28470v2 Announce Type: replace Abstract: Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabil…
- arXiv cs.AIresearchAttention-based representations for multi-task computation
arXiv:2608.04243v1 Announce Type: cross Abstract: Multi-head attention layers produce vector representations that support multiple downstream tasks. We establish bounds on the number of heads required in two simple and c…
- arXiv cs.AIresearchG\"odel's and Scott's Variants of the Ontological Argument in Lean 4 and TPTP THF
arXiv:2609.26806v3 Announce Type: replace-cross Abstract: The Isabelle/HOL dataset of Benzm\"uller and Scott's study of G\"odel's ontological argument and Scott's variant (Monatshefte f\"ur Mathematik, 2025) is carried t…
- arXiv cs.AIresearchLearning Stiffness Dependent Fluid Structure Dynamics from Coarse Flow Representations
arXiv:2609.26816v1 Announce Type: cross Abstract: This paper develops a data-driven framework for long-term prediction of fluid--structure interaction (FSI) dynamics, focusing on the flow-induced vibration (FIV) of a fle…
- arXiv cs.AIresearchSignal2Symbol: Neuro-Symbolic Temporal Reasoning for Explainable Physiological Time-Series Anomaly Detection
arXiv:2609.26820v1 Announce Type: cross Abstract: Physiological time series such as electrocardiograms (ECG) and electroencephalograms (EEG) exhibit complex temporal structure, substantial acquisition variability, and a…
- arXiv cs.AIresearchBridging LLM Serving and CXL-SSDs with Chunk-Aware KV Cache Management
arXiv:2609.26828v1 Announce Type: cross Abstract: NAND-backed storage offers the capacity needed to scale LLM prefix caching, but its block I/O path incurs CPU cache contention and host-DRAM staging in addition to NAND l…
- arXiv cs.AIresearchValidation and Simulation Catch Different Errors: Four Levels of Evaluation for LLM-Generated Circuits
arXiv:2609.26830v1 Announce Type: cross Abstract: Simulation success is not equivalent to structural correctness for LLM-generated circuits. We define and measure four evaluation levels -- schema validity, topological va…
- arXiv cs.AIresearchLWCal: Loss-Weighted Calibration for Tabular Classifiers with Noisy Calibration Labels
arXiv:2609.26839v1 Announce Type: cross Abstract: Post-hoc probability calibration is usually evaluated under an optimistic assumption: the held-out calibration labels are clean. In many AI deployment settings, however,…
- arXiv cs.AIresearchA Leakage-Aware Multimodal Evaluation Framework for Early Intraoperative Acute Kidney Injury Prediction
arXiv:2609.26848v1 Announce Type: cross Abstract: Postoperative acute kidney injury (AKI) after major non-cardiac surgery carries substantial morbidity, yet early intraoperative risk stratification remains difficult. In…
- arXiv cs.AIresearchCOPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation
arXiv:2609.26853v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have achieved remarkable results across various benchmarks, their alignment with normative values often results in homogenized response…
- arXiv cs.AIresearchSsgCaps: A controlled dataset for the evaluation of sound scene generation algorithms
arXiv:2609.26854v1 Announce Type: cross Abstract: Sound Scene Generation is about the automatic synthesis of artificial sound scenes. We introduce SsgCaps, a publicly available dataset of human-engineered sound scenes wh…
- arXiv cs.AIresearchQUARTET: Quad-branch cross-Attention and Random-walk Traces for Enhancing Transformers on Relational Graphs
arXiv:2609.26855v3 Announce Type: replace-cross Abstract: Relational Deep Learning (RDL) models multi-table databases as heterogeneous temporal graphs, and graph transformers currently achieve state-of-the-art performanc…
- arXiv cs.AIresearchFLINT: Fast Lightweight Inference for Traversability
arXiv:2609.26857v1 Announce Type: cross Abstract: Navigation in off-road conditions is challenging due to the lack of structure. There is no fixed vocabulary for what is traversable. The traversability depends on both th…
- arXiv cs.AIresearchComparative Evaluation of Static Embedding Models for HTTP Request Anomaly Detection
arXiv:2609.26860v1 Announce Type: cross Abstract: Web applications are increasingly targeted by cyberattacks that exploit HTTP requests to evade security mechanisms. Traditional web application firewalls (WAFs) rely on r…
- arXiv cs.AIresearchSafety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness
arXiv:2609.26865v2 Announce Type: replace-cross Abstract: Conversational AI systems can pose safety risks to their users such as hallucination, sycophancy, overconfidence, and anthropomorphism, but these risks are diffic…
- arXiv cs.AIresearchCOMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference
arXiv:2609.26913v1 Announce Type: cross Abstract: No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or combine their output…
- arXiv cs.AIresearchCross-Modal Contrastive Learning from Histopathology and CT for Automated Renal Cell Carcinoma Grading
arXiv:2609.26920v1 Announce Type: cross Abstract: Background: Clear cell renal cell carcinoma (ccRCC) exhibits substantial clinical heterogeneity, and accurate grade assessment is essential for risk stratification and tr…
- arXiv cs.AIresearchA 3D Pose-Based Ensemble Framework for Cricket Shot Classification and Automated Biomechanical Analysis
arXiv:2609.26923v1 Announce Type: cross Abstract: Cricket is one of the most celebrated sports world-wide, and technological advancement has become deeply embedded in how the modern game is analyzed and coached. Cricket…
- arXiv cs.AIresearchExperts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation
arXiv:2609.26926v1 Announce Type: cross Abstract: Large-scale text annotation brings expert insight to millions of documents, often through a codebook that AI annotators follow. Developing a robust codebook, however, tak…
- arXiv cs.AIresearchRecognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms
arXiv:2609.26942v1 Announce Type: cross Abstract: Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple choice benchmarks, treating it as a recognition problem. We…
- arXiv cs.AIresearchTopological Signatures of Cyber-Attack Classes in Natural Visibility Graph Representations of Network Traffic
arXiv:2609.26990v2 Announce Type: replace-cross Abstract: Natural Visibility Graph (NVG)-based representations provide a promising approach for capturing structural patterns in sequential network traffic. However, whethe…
- arXiv cs.AIresearchLoss Choice or Model Choice? The Role of Forecast Level in Cryptocurrency Volatility Forecasting
arXiv:2609.27024v1 Announce Type: cross Abstract: Volatility forecasts play a central role in financial risk management because their overall level and day-to-day movements affect downstream decisions. Most studies compa…
- arXiv cs.AIresearchAn open benchmark for machine learning-based polymer property prediction
arXiv:2609.27036v1 Announce Type: cross Abstract: Polymer property prediction lacks open, standardized benchmarks that enable rigorous comparison of machine-learning methods, with existing resources covering only a narro…
- arXiv cs.AIresearchEMA: Elastic and Performance Transparent Memory Across GPUs
arXiv:2609.27040v1 Announce Type: cross Abstract: Multi-GPU servers have become the standard building block of modern data centers, providing aggregated capacity through high-bandwidth interconnects. At the same time, wo…
- arXiv cs.AIresearchThe Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models
arXiv:2609.27070v1 Announce Type: cross Abstract: Modern robot imitation learning increasingly relies on generative policies based on diffusion or flow-matching models, which generate actions by transforming samples from…
- arXiv cs.AIresearchLocal Evidence and Geometric Readout Repair in Trained GNNs
arXiv:2609.27092v1 Announce Type: cross Abstract: Many node-classification GNNs apply a linear classifier to a nonnegative mixture of local messages. An error can reflect either poor mixture weights or a reachable logit…
- arXiv cs.AIresearchWhen Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense
arXiv:2609.27124v1 Announce Type: cross Abstract: Federated Learning enables decentralized model training by exchanging model updates--rather than raw data--with a central parameter server (PS). While most of the existin…
- arXiv cs.AIresearchA Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery
arXiv:2609.27139v1 Announce Type: cross Abstract: Surgical procedures follow a phase-to-step hierarchy, yet the video-language models used to recognize them are evaluated with flat per-level metrics that ignore cross-lev…
- arXiv cs.AIresearchThe Linear Representation Hypothesis Needs a Group Action
arXiv:2609.27158v1 Announce Type: cross Abstract: To make claims about representations that generalize beyond a particular trained model, we need to specify when two representations should count as equivalent. The Linear…
- arXiv cs.AIresearchCount Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement
arXiv:2609.27165v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to measure public value orientations from long social media posts, yet such posts often mix background, quotations, con…
- arXiv cs.AIresearchSelf-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences
arXiv:2609.27175v1 Announce Type: cross Abstract: Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experience. Existing systems…
- arXiv cs.AIresearchPhonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach
arXiv:2609.27205v1 Announce Type: cross Abstract: Text-to-speech systems increasingly process user-generated text (UGT) such as ppl and imo, whose pronunciation must be inferred from the canonical rather than surface for…
- arXiv cs.AIresearchScalable Subgraph Sampling via Resistance Curvature
arXiv:2609.27209v1 Announce Type: cross Abstract: Subgraph sampling reduces the training cost of large-scale graph neural networks, but sampling criteria may overlook the geometric roles of edges. We propose a resistance…
- arXiv cs.AIresearchKATOsuper: Surrogate-accelerated neural topology optimization with sensitivity-consistent Fourier neural operators
arXiv:2609.27216v1 Announce Type: cross Abstract: Topology optimization (TO) remains computationally intensive due to repeated finite element analysis (FEA) evaluations required at each iteration. While neural network-ba…
- arXiv cs.AIresearchLearning Spectral Allocation: A Fractional Diffusion Framework for Adaptive Volumetric Segmentation
arXiv:2609.27217v1 Announce Type: cross Abstract: We address adaptive computation in 3D medical image segmentation: instead of designing another backbone, we ask how much spectral mixing each network stage needs and let…
- arXiv cs.AIresearchMeet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Lattices
arXiv:2609.27225v1 Announce Type: cross Abstract: Probabilistic question-answering systems -- whether large language models (LLMs) themselves, retrieval-augmented generation (RAG), or trained multi-hop retrievers -- conf…
- arXiv cs.AIresearchCombining LLMs and Genetic Search for ARC-AGI-2
arXiv:2609.27242v1 Announce Type: cross Abstract: LLMs can generate programs for ARC-AGI-2 tasks, but the provided compute only allows a small number of attempts to generate, debug and validate solutions. Genetic algorit…
- arXiv cs.AIresearchThe Risk-Sensitive Schr\"odinger Bridge: Is Not a KL Projection
arXiv:2609.27250v1 Announce Type: cross Abstract: The Schr\"odinger bridge owes its computational power to a single structural fact: by Girsanov's theorem the controlled problem is a Kullback--Leibler (KL) projection ont…