AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchBenchmarking Prompt Optimization of Large Language Models With Chess
arXiv:2610.00416v2 Announce Type: replace Abstract: Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamination, and asses…
- arXiv cs.AIresearchFrozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation
arXiv:2610.00447v1 Announce Type: new Abstract: Can a text-to-3D leaderboard change when every generated scene stays fixed? We audit this question for rendered-image evaluation, where camera settings and caption wording…
- arXiv cs.AIresearchOntology-Based Contextual AI Evaluations (OB-CAIE) Methodology
arXiv:2610.00529v1 Announce Type: new Abstract: The ontology-based contextual AI evaluation (OB-CAIE) methodology was developed to address a lack of scientific rigor that arises from unclear testing coverage, to balance…
- arXiv cs.AIresearchScience or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers
arXiv:2610.00531v1 Announce Type: new Abstract: AI-generated content, often called AI slop, is increasingly common everywhere, particularly in academia. Slop in AI-generated scientific papers, however, has more complex p…
- arXiv cs.AIresearchWhen More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization
arXiv:2610.00654v1 Announce Type: new Abstract: Personalization has long relied on customer data to infer what an individual is likely to value. We call this customer evidence: the customer's historical behavior and pref…
- arXiv cs.AIresearchBackdoor Containment via Expert Quarantine and Shutdown in LLMs
arXiv:2610.00663v1 Announce Type: new Abstract: Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-specified outputs under hidden triggers. Existing defenses span four s…
- arXiv cs.AIresearchOntology-Grounded, Reasoner-Verified Benchmarks for Evaluating LLM Reasoning in Scientific AI
arXiv:2610.00682v1 Announce Type: new Abstract: Large language models (LLMs) increasingly underpin scientific AI applications that reason over structured knowledge, from biomedical question answering to materials informa…
- arXiv cs.AIresearchBackdoor Purification for LoRA-Tuned LLMs via Null-Space Projection
arXiv:2610.00685v1 Announce Type: new Abstract: With the rapid adoption of large language models (LLMs) and parameter-efficient fine-tuning (PEFT) methods, the risk of backdoor attacks has become more severe. Existing ba…
- arXiv cs.AIresearchR-GroundBench: A Diagnostic Benchmark for R-Group Groundingin Markush Molecular Editing
arXiv:2610.00700v1 Announce Type: new Abstract: Recent advances in AI for scientific discovery enable molecular understandingand design, yet reasoning over incomplete chemical representations remainsunclear.Markush struc…
- arXiv cs.AIresearchRobust Nash Alignment under Preference Uncertainty
arXiv:2610.00715v1 Announce Type: new Abstract: Preference-based alignment methods typically optimize against a single preference model, and can therefore be brittle when pairwise preferences are uncertain: noisy, hetero…
- arXiv cs.AIresearchEnterprise Representation Simplification (ERS): Reducing Representational Complexity for Enterprise AI
arXiv:2610.00791v1 Announce Type: new Abstract: Enterprise information is represented through artifacts shaped by applications, projects, technologies, organizational boundaries, and local requirements. These structures…
- arXiv cs.AIresearchLearning Multiple Timescales for Goal-Conditioned Reinforcement Learning
arXiv:2610.00849v1 Announce Type: new Abstract: Existing approaches to offline goal-conditioned reinforcement learning (GCRL) struggle with long-horizon tasks. Discounting shrinks value differences between distant states…
- arXiv cs.AIresearchOR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework
arXiv:2610.00912v1 Announce Type: new Abstract: Large language models can translate business descriptions into optimization models, but executable code may misrepresent constraints or objectives. A solver can then return…
- arXiv cs.AIresearchABDA-NL: A Natural-Language Scenario Explorer for Argument-Based Reasoning
arXiv:2610.00947v1 Announce Type: new Abstract: ABDA-NL adds a natural-language interface to ABDA, a system for argument-based discussion using ASPIC- knowledge bases under grounded semantics. Users see which conclusions…
- arXiv cs.AIresearchEvaluating LLM-Generated Preference Distributions
arXiv:2610.01000v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as probabilistic generators for simulation, synthetic data generation, and decision support in settings where real-world…
- arXiv cs.AIresearchCalibration-risk routing for controlled world-model adaptation
arXiv:2610.01001v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) can exploit simulated experience, but a simulator-to-target shift creates a model-selection problem: correcting the simulator…
- arXiv cs.AIresearchWhat Can Analogy Tell Us About Artificial Consciousness?
arXiv:2610.01002v1 Announce Type: new Abstract: Who or what is conscious? Because subjective experience is directly accessible only in the first person, judgments about consciousness in other entities depend partly on an…
- arXiv cs.AIresearchBeyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model
arXiv:2610.01006v1 Announce Type: new Abstract: Decision models return probabilities intended for routing, abstention and automated action. Calibration makes those probabilities useful on average, but does not establish…
- arXiv cs.AIresearchFrom Discovery to Decision: Finite-Budget Recoverability in LLM Voting
arXiv:2610.01014v1 Announce Type: new Abstract: Voting over multiple LLM responses is a common primitive in test-time scaling and ensemble inference. Collecting more responses can expand the candidate pool and increase t…
- arXiv cs.AIresearchNetwork World Models as Environments for Algorithm Design on Complex Systems
arXiv:2610.01048v1 Announce Type: new Abstract: World models, which simulate an environment and predict how it changes under actions, are increasingly used in real-world applications such as robotics. Complex systems cal…
- arXiv cs.AIresearchImproving Math Reasoning through Value-guided Informative Search
arXiv:2610.01080v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the mathematical reasoning capabilities of large language models. Recent work introduces se…
- arXiv cs.AIresearchBeyond State-of-the-Art: Standardising Environmental Impact Metrics for AI Research
arXiv:2610.01116v1 Announce Type: new Abstract: As the capabilities and ubiquity of Large Language Models (LLMs) grow, so does their environmental footprint. Despite calls for responsible AI, the machine learning communi…
- arXiv cs.AIresearchCortexBridge: Cortical Alignment of EEG Montages for Foundation Models
arXiv:2610.01124v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models are often pretrained with a fixed channel vocabulary or a limited set of montages, making transfer difficult when electrode l…
- arXiv cs.AIresearchGrounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting
arXiv:2610.01128v1 Announce Type: new Abstract: Large language models can produce economic policy responses that sound reasonable, but this does not show that their actions are consistent with economic dynamics. We test…
- arXiv cs.AIresearchReSolve: Reusing Candidate Reasoning through Selective Generative Moderation
arXiv:2610.01140v2 Announce Type: replace Abstract: Sampling multiple solutions spends computation on intermediate deductions and unfinished arguments as well as final answers. We introduce ReSolve, a training-free infer…
- arXiv cs.AIresearchWhen Does Exercise-Specific Joint Selection Help? An Audit of Evaluation and Control Design
arXiv:2610.01188v1 Announce Type: new Abstract: Exercise-specific joint selection can improve skeleton-based correctness classification, but what does that gain establish? We audit 1,057 repetitions from ten REHAB24-6 su…
- arXiv cs.AIresearchHHR: Hierarchical Hash Retrieval for Efficient LLM Generation
arXiv:2610.01230v2 Announce Type: replace Abstract: Efficient long-context inference is essential for large language models (LLMs), yet it poses a severe computational bottleneck. Hash-based retrieval offers an efficient…
- arXiv cs.AIresearchLearning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budget
arXiv:2610.01236v1 Announce Type: new Abstract: Collaboration between a small language model (SLM) and a large language model (LLM) offers an opportunity to combine the efficiency of smaller models with the strong reason…
- arXiv cs.AIresearchFeedback Without the Wait: Piloting a Generative AI Practice Platform in a Large Maths Class
arXiv:2610.01262v1 Announce Type: new Abstract: Timely and specific feedback is one of the strongest influences on student learning, yet it is difficult to sustain in large electrical engineering classes where the ratio…
- arXiv cs.AIresearchTrustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics
arXiv:2610.01282v1 Announce Type: new Abstract: The rapid evolution of Intelligent Transportation Systems and Logistics (ITS\&L) has become a cornerstone of the modern social economy, relying heavily on the integration o…
- arXiv cs.AIresearchITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models
arXiv:2610.01296v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) Diffusion Language Models (DLMs) offer flexible parallel decoding and increased model capacity, but their large number of expert parameters incurs…
- arXiv cs.AIresearchQuestionnaire-Guided Disaggregation of Energy Appliance Use for Domestic Smart Meter Data
arXiv:2610.01297v1 Announce Type: new Abstract: Ireland's smart metering programme records electricity use at 30-minute resolution, with smart meters installed in over 80\% of households as of late 2025. While this is us…
- arXiv cs.AIresearchDAYJOB: A Benchmark for Long-Horizon Professional Work
arXiv:2610.01306v1 Announce Type: new Abstract: Professional work often starts with a brief request that leaves the professional to work out what is needed, which documents matter, and whether the request's premise holds…
- arXiv cs.AIresearchProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting
arXiv:2610.01320v1 Announce Type: new Abstract: Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-based methods achieve…
- arXiv cs.AIresearchTRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety
arXiv:2610.01323v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) often refuse a harmful request but comply once the same goal is spread over several turns. Preference objectives score whole res…
- arXiv cs.AIresearchPPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading
arXiv:2610.01325v1 Announce Type: new Abstract: Reinforcement learning for trading often struggles to balance upside participation with drawdown control. Profit-only policies can collapse toward passive long exposure on…
- arXiv cs.AIresearchAn ontology for cross-sectoral crisis management: core and public health modules
arXiv:2610.01326v1 Announce Type: new Abstract: This paper presents the European Crisis Management Ontology (ECMO), a modular OWL-based ontology intended as a cross-sectoral reference for disaster risk reduction and resp…
- arXiv cs.AIresearchGeneration Provenance Before Behavior Attribution: Auditing Synthetic Speech Research Objects
arXiv:2610.01378v1 Announce Type: new Abstract: Attributing model behavior to synthetic training data requires knowing what produced each training item before estimating what that item caused. A waveform-label pair does…
- arXiv cs.AIresearchGacha Decoding: Eliciting Diverse Generations Through Instruction Following
arXiv:2610.01382v1 Announce Type: new Abstract: We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. Across open-ended domains (in-the-…
- arXiv cs.AIresearchPRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal Analogies
arXiv:2610.01383v2 Announce Type: replace Abstract: Analogical reasoning involves identifying and preserving relational structures across domains. However, existing approaches to AI-driven multimodal analogy generation l…
- arXiv cs.AIresearchAiSearch: Interactive Multi-Modal Search with VLMs
arXiv:2610.01389v1 Announce Type: new Abstract: Modern retrieval systems must both be automated and interactive, allowing users to search and refine results in real time. We present AiSearch, a flexible multimodal retrie…
- arXiv cs.AIresearchContrastive Attention Mitigates Spectral Bias in Spiking Transformers
arXiv:2610.01403v1 Announce Type: new Abstract: Spiking Transformers merge the energy-efficiency of spiking neural networks (SNNs) with the representational power of self-attention, creating a promising architecture for…
- arXiv cs.AIresearchSpikeMoE: Brain-Inspired Competitive Routing for Flexible Spiking Mixture-of-Experts
arXiv:2610.01418v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) enable event-driven computation through biologically inspired dynamics at the neuronal scale, while Mixture-of-Experts (MoE) perform cond…
- arXiv cs.AIresearchA Deterministic and Auditable AI Security Risk Assessment Framework with ATLAS Aligned Executable Rules and Formal Verification
arXiv:2610.01436v1 Announce Type: new Abstract: Artificial intelligence systems are increasingly deployed in high impact and safety critical settings, yet security assessment remains difficult to reproduce and defend und…
- arXiv cs.AIresearchDRelay: Global Draft Context for Prefix-Aware Parallel Speculative Decoding Repair
arXiv:2610.01439v1 Announce Type: new Abstract: Parallel drafting reduces the drafting overhead of speculative decoding for large language models (LLMs), but its gains remain limited by the accepted prefix length. Even w…
- arXiv cs.AIresearchRethinking Probability-Based Reinforcement Learning From Posterior Concentration
arXiv:2610.01458v3 Announce Type: replace Abstract: Verifier-free reinforcement learning with probability-based rewards offers a promising way to train LLMs on general reasoning tasks where external verifiers are unavail…
- arXiv cs.AIresearchNextMe-800: Anticipating Personal Behavior from Months of Egocentric Video
arXiv:2610.01461v1 Announce Type: new Abstract: We often plan ambitiously yet act habitually and wonder, in retrospect, whether we would have planned differently had we known what we would actually do. Hindsight offers a…
- arXiv cs.AIresearchAuditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers
arXiv:2610.01495v1 Announce Type: new Abstract: Dynamic architectures leave a per-example routing trace beside each prediction, and diffuse routing is easy to read as a sign that the prediction is unreliable. We audit th…
- arXiv cs.AIresearchSharpening Tax in Post-Training
arXiv:2610.01509v1 Announce Type: new Abstract: An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improv…
- arXiv cs.AIresearchDecision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning
arXiv:2610.01513v1 Announce Type: new Abstract: Long-term dependencies remain a major challenge for sequential decision-making in the field of AI: RNNs suffer from vanishing gradients and the limited expressivity of vect…