AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchHuman-AI-Powered Hypothesis Testing: Cost-Aware Selective AI Scoring and Sequential Human Escalation
arXiv:2609.28859v1 Announce Type: new Abstract: Large language models are increasingly used as inexpensive judges to evaluate outputs, label data, and assess whether a system meets a desired quality standard. Yet using A…
- arXiv cs.AIresearchPFArena: Benchmarking Language Models for Protein Modification
arXiv:2609.28921v1 Announce Type: new Abstract: Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational paradigms including pro…
- arXiv cs.AIresearchFrom Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs
arXiv:2609.28942v1 Announce Type: new Abstract: Personalized value alignment has become increasingly important as large language models (LLMs) are expected to accommodate diverse user preferences. However, existing metho…
- arXiv cs.AIresearchCRISS: A Retrieval-Augmented AI Chatbot for Assisting Cancer Registrars
arXiv:2609.29075v1 Announce Type: new Abstract: Cancer registrars, including Oncology Data Specialists (ODSs), must interpret complex and frequently updated coding and staging standards. We developed CRISS (Cancer Regist…
- arXiv cs.AIresearchA Rapid Pipeline for Training and Deploying ML Models on WeBe Band
arXiv:2609.29084v1 Announce Type: new Abstract: Developing optimized machine-learning algorithms for edge devices with limited computational and memory resources is challenging, time-consuming, and highly dependent on de…
- arXiv cs.AIresearchFunctional Architecture of European Electricity Trading Markets: Requirements for AI Supported Trading Systems under Regulatory Constraints
arXiv:2609.29108v2 Announce Type: replace Abstract: European electricity trading in the EU operates as a constrained multi-layer system in which legal design, exchange microstructure, and network physics are executed joi…
- arXiv cs.AIresearchCounterRoute: Self-Routed Reasoning via Hierarchical Counterfactual Credit Assignment
arXiv:2609.29109v2 Announce Type: replace Abstract: Reasoning-capable language models often produce long chains of thought when direct answers suffice, wasting inference compute. Dual-mode models offer both thinking and…
- arXiv cs.AIresearchSharp Limits for Honest Uncertainty in Hard-Budget Repeated Evaluation
arXiv:2609.29140v1 Announce Type: new Abstract: Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty. We characterize that requirement on a fixed g…
- arXiv cs.AIresearchClaim-Gated Source-Risk Auditing for Generative Search
arXiv:2609.29145v2 Announce Type: replace Abstract: A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the query-sour…
- arXiv cs.AIresearchRight Choice of Classification Algorithms Based on Reinforcement Learning for Prediction of Non-Alcoholic Fatty Liver
arXiv:2609.29181v1 Announce Type: new Abstract: There are many complex issues in the world of artificial intelligence. Some of these problems are solved using other artificial intelligence methods, which are called artif…
- arXiv cs.AIresearchThe Entropy Triangle Method (ETM): A novel framework for the prevention of cardiac arrhythmia with a review of more than 10,000 patients
arXiv:2609.29187v1 Announce Type: new Abstract: One of the most important problems in medicine is to facilitate prediction. In this study, we propose entropy triangle method, a novel framework for predicting heart rhythm…
- arXiv cs.AIresearchBaszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier
arXiv:2609.29266v1 Announce Type: new Abstract: We develop a multi-label Polish content-safety classifier by fine-tuning allegro/herbert-base-cased (124M) across five categories (hate, vulgarity, sexual content, crime, s…
- arXiv cs.AIresearchALOE: Semantically Addressed Low-Rank Operators for Knowledge Editing
arXiv:2609.29269v1 Announce Type: new Abstract: Knowledge editing changes what a model knows by modifying parameters so that a requested fact updates while unrelated behavior is preserved. This is usually treated as a wr…
- arXiv cs.AIresearchFrom Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model
arXiv:2609.29283v1 Announce Type: new Abstract: Visual software often needs a decision over supplied alternatives rather than a generated explanation. We present PixelJev, a native-image decision interface that maps an i…
- arXiv cs.AIresearchWhen No One Owns the Judgment: Accountability Under Contribution Dissolution in Human-AI Collaboration
arXiv:2609.29312v2 Announce Type: replace Abstract: Communities often respond to potentially AI-assisted work by asking three questions: Was AI used? Was that use disclosed? Can hidden use be detected? These questions pl…
- arXiv cs.AIresearchThe Last Human Gate: Forward Deployed Engineering for Governance Automation
arXiv:2609.29345v1 Announce Type: new Abstract: Enterprise governance requires decisions, evidence, and accountable authority; it does not require every review task to retain its current human implementation. We develop…
- arXiv cs.AIresearchBeyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses
arXiv:2609.29363v1 Announce Type: new Abstract: The public visibility of Artificial Intelligence (AI) is growing rapidly, driven by the positive impact of its applications across diverse fields of knowledge. In this new…
- arXiv cs.AIresearchAn auditable conditional-strategy framework for open-ended decision-making in complex lung cancer
arXiv:2609.29381v2 Announce Type: replace Abstract: Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effective support must…
- arXiv cs.AIresearchWearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach
arXiv:2609.29396v1 Announce Type: new Abstract: This paper presents and evaluates a Deep Learning-based (DL-based) Signal Quality Assessment (SQA) model to distinguish between clean and noisy ambulatory Electrocardiogram…
- arXiv cs.AIresearchRD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations
arXiv:2609.29403v1 Announce Type: new Abstract: Learning surrogates for time-dependent partial differential equations often requires a new simulation corpus when the governing operator changes. We introduce RD-JEPA, a jo…
- arXiv cs.AIresearchJust Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
arXiv:2609.29429v1 Announce Type: new Abstract: Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, an…
- arXiv cs.AIresearchBiGraph-Diffuse: A Bidirectional Diffusion Language Model with Graph-Structured Retrieval For Mental Health Counseling
arXiv:2609.29519v1 Announce Type: new Abstract: Mental health disorders affect hundreds of millions of people around the world, yet access to professional counseling remains severely limited. AI-powered dialogue systems…
- arXiv cs.AIresearchClinical Knowledge Graphs for Chest X-Ray Device Reasoning
arXiv:2609.29536v1 Announce Type: new Abstract: Chest radiographs are routinely used to verify the position of catheters, tubes, and other support devices. Existing image models often return labels or segmentations, whil…
- arXiv cs.AIresearchHiPACE: Hierarchical Phase-Boundary Analysis and Controlled Evaluation of Feature Absorption in Sparse Autoencoders
arXiv:2609.29551v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose LLM activations into sparse dictionary atoms, so that each distinct concept gets its own feature. One recurring behavior complicates th…
- arXiv cs.AIresearchCross-Modal Emotion Understanding: A Transformer-GAT Approach for Dialogue Emotion Recognition
arXiv:2609.29556v2 Announce Type: replace Abstract: Multimodal emotion recognition is a key research area in affective computing, with applications in sentiment analysis, intelligent customer service, and human-computer…
- arXiv cs.AIresearchIs Reasoning Always Useful? Rethinking Reasoning Utility in Universal Multimodal Embeddings
arXiv:2609.29560v1 Announce Type: new Abstract: Reasoning-enhanced universal multimodal embeddings (UME) improve heterogeneous retrieval, but plausible rationales do not necessarily produce discriminative rankings. We st…
- arXiv cs.AIresearchSequential knowledge editing breaks a model's ability to tell good evidence from bad, without costing it accuracy
arXiv:2609.29587v1 Announce Type: new Abstract: Knowledge editing is evaluated on whether the edited fact changed, whether paraphrases follow, and whether unrelated answers stayed put. A model can pass all three and stil…
- arXiv cs.AIresearchPEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging
arXiv:2609.29599v1 Announce Type: new Abstract: Normal-inverse-gamma (NIG) regression is not uniquely identifiable from its marginal Student-t likelihood: the likelihood determines three combinations of four NIG paramete…
- arXiv cs.AIresearchiCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model
arXiv:2609.29626v1 Announce Type: new Abstract: Recursive AI, the prospect of AI taking an increasingly complete role in building and improving AI, is a crown jewel of AI for AI. Although recursive self-development has b…
- arXiv cs.AIresearchTo Think or Not to Think: Allocating Reasoning Where It Helps
arXiv:2609.29664v1 Announce Type: new Abstract: Reinforcement learning (RL) has proven effective in enhancing the reasoning performance of large language models (LLMs), particularly in complex mathematical and programmin…
- arXiv cs.AIresearchFair Like Us? Auditing LLM Alignment in Resource Allocation
arXiv:2609.29692v1 Announce Type: new Abstract: Fair allocation of scarce, indivisible resources is an important challenge in many societal problems. While there are several formal theories of fairness, no single definit…
- arXiv cs.AIresearchA General Framework for Budgeted Threshold Incentives on Request
arXiv:2609.29724v1 Announce Type: new Abstract: On-demand delivery platforms pay riders through incentive activities whose tiers are set from recent completions of riders with a similar history. Operators request such pl…
- arXiv cs.AIresearchThe Gold in Bias: Maturing the AI Design Process through Verification
arXiv:2609.29730v1 Announce Type: new Abstract: Bias in AI systems is typically framed as a flaw to be minimized, yet it also serves as a critical indicator of underlying weaknesses in data, modeling assumptions, and sys…
- arXiv cs.AIresearchC3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks
arXiv:2609.29735v1 Announce Type: new Abstract: Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained…
- arXiv cs.AIresearchAI-based detection of worsening heart failure from low-resolution telemonitoring data
arXiv:2609.29742v1 Announce Type: new Abstract: Objective: Heart failure (HF) presents a healthcare challenge due to its high comorbidity burden, aging patient population and frequent hospitalizations. Remote monitoring…
- arXiv cs.AIresearchHallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons
arXiv:2609.29781v1 Announce Type: new Abstract: Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claimed to detect and caus…
- arXiv cs.AIresearchLearning to Ideate for Scientific Impact
arXiv:2609.29802v1 Announce Type: new Abstract: Scientific ideation is increasingly mediated by large language models, but current ideation systems are usually trained and evaluated on immediately judgeable proxies such…
- arXiv cs.AIresearchDecoding Imagined Speech: A Strictly Subject-Independent Approach Using EEG
arXiv:2609.29820v1 Announce Type: new Abstract: Imagined speech decoding from electroencephalography (EEG) has gained increasing attention as a potential communication pathway for individuals with severe motor impairment…
- arXiv cs.AIresearchA Risk-Adaptive and Evidence-Constrained Framework for Generative AI Feedback in Programming Education
arXiv:2609.29874v1 Announce Type: new Abstract: Generative artificial intelligence can turn learning analytics into personalized support, but feedback systems must decide when to intervene, which evidence to use, and how…
- arXiv cs.AIresearchOntology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholders
arXiv:2609.29876v1 Announce Type: new Abstract: Neurosymbolic research typically assumes a pre-existing symbolic specification, leaving the upstream challenge of acquiring and formalizing requirements and constraints lar…
- arXiv cs.AIresearchNeuro-symbolic AI for Industrial Configuration
arXiv:2609.29947v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown impressive performance on a wide range of generative tasks. Yet their probabilistic nature makes them, in isolation, fundamentally u…
- arXiv cs.AIresearchENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation
arXiv:2609.29948v1 Announce Type: new Abstract: Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or predefined target responses. We…
- arXiv cs.AIresearchAugur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes
arXiv:2609.29952v1 Announce Type: new Abstract: Before a product or policy change ships, the question that matters is how people will react to it. Augur rehearses that reaction offline: it builds a typed knowledge graph…
- arXiv cs.AIresearchStyle, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models
arXiv:2609.30048v1 Announce Type: new Abstract: If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We test this zero-shot o…
- arXiv cs.AIresearchNNV3: Expanding Neural Network Verification to New Architectures and Domains
arXiv:2609.30050v1 Announce Type: new Abstract: We present NNV3, the latest version of the Neural Network Verification (NNV) tool, a MATLAB framework for formal verification of deep learning models and learning-enabled c…
- arXiv cs.AIresearchSciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback
arXiv:2609.30054v1 Announce Type: new Abstract: Improving the scientific coding capabilities of large language models (LLMs) requires high-quality training data. However, such data remain scarce because manually authorin…
- arXiv cs.AIresearchSelf-Play Pretraining with Zero Data
arXiv:2609.30063v1 Announce Type: new Abstract: Advances in language modeling have been driven by scaling pretraining on ever more data. Yet, the training data is still largely curated on the model's behalf. A more gener…
- arXiv cs.AIresearchEnigmaForge: The Question Is Hidden in the Story
arXiv:2609.30144v1 Announce Type: new Abstract: Most benchmarks hand the model a question. EnigmaForge hands it a stack of old documents and no question at all. Buried in the letters, receipts, and logbook margins is a s…
- arXiv cs.AIresearchSearch-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search
arXiv:2609.30177v2 Announce Type: replace Abstract: Query understanding (QU) in production search systems has typically relied on separate models for each subtask, such as search intent classification, attribute extracti…
- arXiv cs.AIresearchSAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
arXiv:2609.30192v1 Announce Type: new Abstract: Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induc…