AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchUnderstanding When Reflective Prompt and Skill Optimization Helps on Locally Served Reasoning Models: A Two-Model Study of GEPA and SkillOpt
arXiv:2610.26020v1 Announce Type: new Abstract: Reflective text-space optimizers such as GEPA and SkillOpt have reported large gains on frontier and mid-size models. We test replication across two reasoning-native target…
- arXiv cs.AIresearchFinSafeGuard: A Quality-Driven Synthetic Dataset for Financial AI Safety
arXiv:2610.26066v1 Announce Type: new Abstract: Generating high-quality synthetic datasets at scale remains a fundamental challenge for training specialized AI systems in data-scarce domains. We present a comprehensive m…
- arXiv cs.AIresearchMoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching
arXiv:2610.26185v2 Announce Type: replace Abstract: Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluat…
- arXiv cs.AIresearchOn Counting Graphs for Modal Logic with Counting
arXiv:2610.26187v1 Announce Type: new Abstract: In this paper, we study the theoretical computational complexity of counting trees and graphs that are classified positively by a graph neural networks, or said equivalentl…
- arXiv cs.AIresearchLLMs Prompted for Legal Context Refuse More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
arXiv:2610.26211v1 Announce Type: new Abstract: Confidentiality requirements increasingly push legal professionals toward small, on-device LLMs that keep case data in-house, used for everyday tasks such as summarization,…
- arXiv cs.AIresearchFairness or Fallacy? Mapping the Landscape of AI Bias in Disease Detection
arXiv:2610.26215v1 Announce Type: new Abstract: Artificial intelligence (AI) has several transformative effects on healthcare, like to facilitate clinicians in disease detection and to manage patient care with enhanced p…
- arXiv cs.AIresearchTowards More Granular Reasoning: Mapping the DSA Transparency Database Taxonomy to Platform Terms and Conditions Using Large Language Models
arXiv:2610.26226v1 Announce Type: new Abstract: Article 24(5) of the Digital Services Act (DSA) requires providers of online platforms to submit every content moderation decision they make, with a corresponding Statement…
- arXiv cs.AIresearchCoRS: Fast Neural Flexible Job-Shop Scheduling via Composite Interval State Reuse
arXiv:2610.26239v1 Announce Type: new Abstract: Neural solvers for the Flexible Job-Shop Scheduling Problem (FJSP) typically refresh graph representations and update feasibility after every operation--machine decision. H…
- arXiv cs.AIresearchMachina Pauliana: A neuro-symbolic approach to the actio pauliana in Dutch insolvency law
arXiv:2610.26241v1 Announce Type: new Abstract: Applying a legal provision frequently requires both structured rule-based reasoning and sensitivity to open-textured terms developed in case law. The actio pauliana of Arti…
- arXiv cs.AIresearchBeyond Static Leaderboards: Capability-Focused Evaluation with Structural Diversity for Time Series Foundation Models
arXiv:2610.26251v1 Announce Type: new Abstract: Static public benchmarks for time series foundation models (TSFMs) typically have fixed and narrow test distributions. Their repeated reuse encourages benchmark-specific tu…
- arXiv cs.AIresearchLOCU: Lowdin-Orthogonalized Constraint Updates for Multi-Constraint Policy Optimization
arXiv:2610.26256v1 Announce Type: new Abstract: We investigate multi-constraint policy optimization in constrained Markov decision processes (CMDPs), where interactions among constraint gradients often yield ill-conditio…
- arXiv cs.AIresearchREFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
arXiv:2610.26261v3 Announce Type: replace Abstract: RNA molecules often function through multiple experimentally observed conformational states. A central challenge is to capture ensemble diversity without sacrificing st…
- arXiv cs.AIresearchSelective Transfer through Sequence Distillation: From Benchmark Knowledge to Backdoor Behaviour
arXiv:2610.26311v1 Announce Type: new Abstract: Knowledge distillation is widely used to transfer capabilities from teacher models to student models, but recent work shows that it can also transfer unintended teacher pro…
- arXiv cs.AIresearchStrucChunk: Structure-Aware Retrieval for Legal Document RAG
arXiv:2610.26313v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) can ground LLM outputs in domain-specific knowledge, but legal documents are hard: standard chunking fragments hierarchical argument st…
- arXiv cs.AIresearchA Generic On-Board AI Processing Chain for Earth Observation: From Application Development to Embedded Deployment and Mission-Level Orchestration
arXiv:2610.26340v1 Announce Type: new Abstract: Earth observation satellites acquire more data than they can downlink. Extracting information on board with artificial intelligence (AI) turns the satellite into a data-red…
- arXiv cs.AIresearchCARRS: A Constraint-Aware, Real-Time Routing System for Emergency Vehicles in Urban Environments
arXiv:2610.26346v1 Announce Type: new Abstract: Emergency vehicles such as police vehicles, fire engines, and ambulances require a stable and efficient route optimization to reach life-critical events in the shortest tim…
- arXiv cs.AIresearchGAIDA: Generative AI for Human-in-the-Loop Document Annotation
arXiv:2610.26362v1 Announce Type: new Abstract: Document annotation is a fundamental yet labor-intensive step in building document information extraction systems. While Optical Character Recognition (OCR) and Large Langu…
- arXiv cs.AIresearchBOSS: Token-Budgeted Online Sampling and Selection for LLM Reasoning
arXiv:2610.26383v1 Announce Type: new Abstract: Test-time scaling can improve LLM reasoning, but existing approaches typically adapt generation or apply answer selection after a predetermined generation schedule. We stud…
- arXiv cs.AIresearchAnswer Delivery Under a Shared Token Budget: An Audited Study of Stopping and Finalization
arXiv:2610.26384v1 Announce Type: new Abstract: An inference budget is useful only when the system delivers an answer within it. We study a fixed-budget policy combining first-valid-box stopping with a charged finalizati…
- arXiv cs.AIresearchLocal data augmentation for imbalanced binary classification
arXiv:2610.26418v1 Announce Type: new Abstract: Facing imbalanced binary classification, we aim at maximizing the recall while limiting the proportion of false detections in the minority class. For doing that, the presen…
- arXiv cs.AIresearchPhysiology-Aware Graph Attention for Early Ventricular Reentry Prediction
arXiv:2610.26430v1 Announce Type: new Abstract: Sudden cardiac death mostly originates from post-infarct ventricular tachycardia. This reentry is sustained by propagation around scar tissue, but its risk remains difficul…
- arXiv cs.AIresearchRouterWorld: Scaling Conversational AI with Latency-Aware LLM Routing
arXiv:2610.26511v1 Announce Type: new Abstract: Conversational AI systems built on Large Language Models (LLMs) require routing mechanisms that balance answer quality and response latency at scale. However, existing LLM…
- arXiv cs.AIresearchToward Structured Financial Foundation Models
arXiv:2610.26516v1 Announce Type: new Abstract: Foundation models promise reusable capabilities and step-change performance gains across tasks. In finance, large-scale pretraining of domain-specialized foundation models…
- arXiv cs.AIresearchBeyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulation
arXiv:2610.26524v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as user simulators, but can they faithfully reproduce an individual's behavior and decision logic over time? We inves…
- arXiv cs.AIresearchBreaking Diffusion: Parallel Reasoning with Draft Refinement
arXiv:2610.26542v1 Announce Type: new Abstract: Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually pla…
- arXiv cs.AIresearchTraining Natural Schemers: RL Can Amplify Oversight-Conditional Behavior
arXiv:2610.26551v2 Announce Type: replace Abstract: One of the central concerns for the safety of advanced AI is scheming: when a model strategically complies under oversight but pursues its own goals when unobserved. Cu…
- arXiv cs.AIresearchWhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting
arXiv:2610.26582v2 Announce Type: replace Abstract: Recent time series foundation models (TSFMs) can consume covariates in-context, extending zero-shot forecasting to problems driven by external factors. This enables sce…
- arXiv cs.AIresearchRevision-Based Learning from Interactive Experience and Feedback
arXiv:2610.26636v2 Announce Type: replace Abstract: Code generation models are increasingly used to produce interactive artifacts, such as websites and user interfaces. Many properties that determine whether these interf…
- arXiv cs.AIresearchFrom Outcomes to Components: A Counterfactual Evaluation Framework for LLM-Proposed Repairs
arXiv:2610.26650v2 Announce Type: replace Abstract: A repair action proposed by a large language model (LLM) specifies which records to change and how to change their values. A failed action may still contain a useful ch…
- arXiv cs.AIresearchTowards Robust Model Organisms for Eliciting Latent Knowledge
arXiv:2610.26698v1 Announce Type: new Abstract: A key problem in AI safety is eliciting latent knowledge (ELK), extracting information from a model that is misaligned and more knowledgeable than its overseer. For example…
- arXiv cs.AIresearchLG-Bench: A Graph-Structured Evaluation Benchmark for Life Sciences
arXiv:2610.26787v1 Announce Type: new Abstract: Traditional evaluation benchmarks reduce inherently interconnected scientific knowledge in life sciences into flat lists of questions, disregarding the underlying topologic…
- arXiv cs.AIresearchSOMA: Continuous Monitoring and Intervention for System Two Reasoning with System One Models
arXiv:2610.26793v1 Announce Type: new Abstract: Reasoning models often run into problems without noticing them, even when symptoms are visible in their own text. In humans, metacognition separates monitoring from control…
- arXiv cs.AIresearchTransfer Learning for Power Outage Detection Task with Limited Training Data
arXiv:2305.17817v1 Announce Type: cross Abstract: Early detection of power outages is crucial for maintaining a reliable power distribution system. This research investigates the use of transfer learning and language mod…
- arXiv cs.AIresearchMulti-LLM Systems Exhibit Robust Semantic Collapse
arXiv:2605.17193v3 Announce Type: cross Abstract: Whether machines can originate novel content has been debated for nearly two centuries, from Lovelace's assertion that no engine can "originate anything" to Turing's ques…
- arXiv cs.AIresearchSAMPA: Transformer-based segmentation of prosodic boundaries in Brazilian Portuguese
arXiv:2607.07408v3 Announce Type: replace-cross Abstract: Automatic prosodic segmentation identifies boundaries between speech units based on acoustic and linguistic evidence. Although recent deep learning approaches hav…
- arXiv cs.AIresearchCan the Quantum Fisher Effective Dimension Judge a Hybrid Quantum Neural Network?
arXiv:2610.14070v1 Announce Type: cross Abstract: Hybrid quantum neural networks (QNNs) pair a classical feature extractor with a variational quantum circuit, and the effective dimension of the circuit's quantum Fisher i…
- arXiv cs.AIresearchAnytime Contracts for AI Services
arXiv:2610.22781v1 Announce Type: cross Abstract: AI services are prone to moral hazard, as model providers can silently route requests to cheaper, lower-quality models, and the inherent stochasticity of model outputs ma…
- arXiv cs.AIresearchLLM-Assisted Bi-Approximate CHC Solving
arXiv:2610.23771v1 Announce Type: cross Abstract: Constrained Horn clause (CHC) solvers often struggle to discover deep counterexamples whose derivations may require extensive rule unfolding. Although large language mode…
- arXiv cs.AIresearchComposable Parametric Demographic Injection for Values Survey Simulation
arXiv:2610.23867v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as simulated respondents in computational social science, yet accurately reproducing population-specific heterogeneous…
- arXiv cs.AIresearchGeoForward: Geometry-Guided Cross-View Alignment for Feedforward 3D Gaussian Splatting
arXiv:2610.23895v1 Announce Type: cross Abstract: Feedforward 3D reconstruction has largely followed an {appearance-driven paradigm}: multi-view images are encoded into visual representations, cross-view correspondence i…
- arXiv cs.AIresearchEgoVine: Post-Training with Branching Experience Compiled from Real-World Videos
arXiv:2610.23907v1 Announce Type: cross Abstract: Real-world egocentric videos capture multi-step household procedures, but their recorded trajectories leave alternative actions and recovery from the learner's own mistak…
- arXiv cs.AIresearchWhen the Editing Intent Is Split: A Cross-Modal Jailbreak Attack for Large Image Editing Models
arXiv:2610.23909v1 Announce Type: cross Abstract: Large image editing models increasingly infer editing intent from both textual and visual inputs, creating an underexplored safety risk when harmful intent is distributed…
- arXiv cs.AIresearchUMI-WM: Interactive World Modeling for Bimanual Manipulation from Wrist Cameras
arXiv:2610.23913v1 Announce Type: cross Abstract: Universal Manipulation Interface (UMI) pairs wrist-camera videos with camera trajectories and gripper openings, providing scalable, robot-free data for learning how biman…
- arXiv cs.AIresearchSPIRIT: Sparse Physics-Informed Inverse Rendering for SAR Imaging
arXiv:2610.23914v1 Announce Type: cross Abstract: Radio-frequency (RF) and wave-based imaging systems play a critical role in sensing under adverse conditions, but are fundamentally constrained by a trade-off between col…
- arXiv cs.AIresearchCross-Modal Forgetting and Transfer in Unified Multimodal Post-Training
arXiv:2610.23918v1 Announce Type: cross Abstract: Unified multimodal models answer questions about images and also generate images with one shared set of weights. This creates a post-training risk that single-purpose mod…
- arXiv cs.AIresearchZero-Shot Tabular Learning via Hypergraph Reasoning with LLMs
arXiv:2610.23923v1 Announce Type: cross Abstract: Tabular data are prevalent across diverse domains such as healthcare and finance. Zero-shot tabular learning aims to make predictions without labeled data. However, exist…
- arXiv cs.AIresearchSpinDoctor: Finding Innocuous Prompts for Biased Image Generation
arXiv:2610.23925v1 Announce Type: cross Abstract: We introduce SpinDoctor, a method for discovering innocuous prompts for text-to-image models that result in images with a chosen target bias, while retaining the quality…
- arXiv cs.AIresearchImproving Fake Profile Detection Through Multimodal Learning and Research-Guided Feature Integration
arXiv:2610.23926v1 Announce Type: cross Abstract: Fake accounts continue to undermine online platforms, yet it remains unclear whether multimodal learning offers meaningful improvements over strong metadata baselines or…
- arXiv cs.AIresearchminiTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning
arXiv:2610.23928v1 Announce Type: cross Abstract: Native NVFP4 promises to accelerate reinforcement learning (RL) for large language models (LLMs), but achieving stable learning across separate training and sampling engi…
- arXiv cs.AIresearchOrganizing LLM Inference for Aggregate Predictions from Behavioral Data
arXiv:2610.23934v1 Announce Type: cross Abstract: When using a large language model (LLM) to simulate a user population, how should we combine individual behavioral histories to predict the fraction of users who take a p…