AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchScaling Laws for Generative Reward Models
arXiv:2610.30765v1 Announce Type: new Abstract: We study generative reward models (GenRMs) as online preference providers for policy optimization in creative writing. Across Qwen3 reward-model sizes from 0.6B to 14B, Thi…
- arXiv cs.AIresearchProQuant: Preserving Expert Quality over Quantity in Ultra-Low-Bit Quantization of Mixture-of-Experts Models
arXiv:2610.30779v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) large language models reduce computation through sparse activation but still incur substantial storage costs. Mixed-precision post-training quantiz…
- arXiv cs.AIresearchWhat Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight
arXiv:2610.30803v1 Announce Type: new Abstract: Replacing the judge can move a benchmark score, and models can be trained to hide capabilities. Both put the evaluator in question: what can it certify? We develop a partit…
- arXiv cs.AIresearchTESSA: A Governance-Oriented Custom GPT for SME Guidance under the EU AI Act: Design, Implementation, and Evaluation
arXiv:2610.30822v1 Announce Type: new Abstract: The increasing adoption of generative AI presents new opportunities while raising AI governance and regulatory challenges, particularly for small and medium-sized enterpris…
- arXiv cs.AIresearchSemi-Linear Gaussian Bayesian Networks: Enhancing Flexibility in Node Dependencies via penalized B-Splines
arXiv:2610.30838v1 Announce Type: new Abstract: Bayesian networks for continuous variables often rely on restrictive assumptions: linear Gaussian models lack flexibility to capture nonlinear dependencies, while non-param…
- arXiv cs.AIresearchParameter Learning in Active Inference via Variational Message Passing
arXiv:2610.30899v1 Announce Type: new Abstract: Active inference casts perception, learning and planning as variational inference, where the Expected Free Energy (EFE) defines the planning objective. Recent work showed t…
- arXiv cs.AIresearchBeyond Phenotypic Similarity: Relation Refinement and Selective Population Graph Learning for Multimodal Brain Disorder Diagnosis
arXiv:2610.30902v1 Announce Type: new Abstract: Population graph learning supports brain disorder diagnosis by sharing information across subjects. Its effectiveness, however, depends on whether the relationships guiding…
- arXiv cs.AIresearchTwinStore: A Synthetic Consumer Platform Using Vision--Language Models
arXiv:2610.30909v1 Announce Type: new Abstract: We present TwinStore, a source-available synthetic consumer platform for physical retail built on vision--language models. TwinStore turns a store into a digital twin---fro…
- arXiv cs.AIresearchDConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding
arXiv:2610.30920v1 Announce Type: new Abstract: Diffusion language models (DLMs) decode multiple tokens in parallel, so individually valid tokens can be incompatible together under a schema. Exact joint inference over a…
- arXiv cs.AIresearchThe Geometry of Meaning in Neural Manifolds
arXiv:2610.30938v1 Announce Type: new Abstract: Just as different languages express the same concept through different words, neural networks express similar functions through incompatible coordinate systems. Different a…
- arXiv cs.AIresearchMeasuring the Reasoning-Action Coupling in Driving Vision-Language-Action Models through Counterfactuals
arXiv:2610.30953v1 Announce Type: new Abstract: Driving vision-language-action (VLA) models bring an appealing form of explainability to a safety-critical domain, since a system that can state the reasons for its maneuve…
- arXiv cs.AIresearchZero-Shot Forecasting of In-Situ Soil Moisture and Temperature with a Time-Series Foundation Model
arXiv:2610.30971v1 Announce Type: new Abstract: Soil moisture and temperature govern plant-water availability and microbial activity, making them key indicators for evaluating land-restoration efforts on degraded landsca…
- arXiv cs.AIresearchAgri-SCHOLAR: Simulation-Grounded In-Season Rolling Advisories for Agricultural Crops Using LLM-Bounded Optimization
arXiv:2610.31003v1 Announce Type: new Abstract: Existing agricultural advisories to farmers suffer from several limitations: (a) remain largely expert-driven, (b) do not adequately account for in-season weather, and (c)…
- arXiv cs.AIresearchMitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment
arXiv:2610.31005v2 Announce Type: replace Abstract: Long-text image-text alignment is essential for fine-grained scene understanding, yet existing methods mainly focus on extending context length or improving local align…
- arXiv cs.AIresearchEvaluating Artificial Wisdom (AW): A Trajectory-Based Framework for Context-Sensitive Decision Regulation
arXiv:2610.31012v1 Announce Type: new Abstract: Capability benchmarks measure what large language models can do, but not whether their recommendations remain appropriate as decision conditions change. This paper proposes…
- arXiv cs.AIresearchMultichoice Modeling: Exploring Decision Configuration Space under Uncertainty
arXiv:2610.31038v1 Announce Type: new Abstract: Decision support has become sophisticated at exploring uncertainty, but much less so at representing the architecture of the decision itself. As a result, the decision spac…
- arXiv cs.AIresearchAlgorithmic drift in generative adaptive learning
arXiv:2610.31041v1 Announce Type: new Abstract: Generative artificial intelligence promises to democratize personalized tutoring, yet the longitudinal stability of adaptive systems remains under-theorized. Current ethica…
- arXiv cs.AIresearchConflict-Aware Logit Adapters for Utility-Preserving Anti-Distillation
arXiv:2610.31046v1 Announce Type: new Abstract: While reasoning traces improve model capability, they also provide supervision signals for downstream distillation. Initial efforts to mitigate this issue rely on decoding-…
- arXiv cs.AIresearchDirecting to Diversify: Multi-Directional Search for Automatic Heuristic Design
arXiv:2610.31048v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong potential to automate heuristic design for NP-hard combinatorial optimization (CO) tasks without human intervention. R…
- arXiv cs.AIresearchDiagnosing the Explicit-to-Applied Theory of Mind Gap in LLMs
arXiv:2610.31060v1 Announce Type: new Abstract: As large language models are deployed in high-stakes roles such as therapy, education, and personal assistance, their social cognition must be assessed reliably. Current Th…
- arXiv cs.AIresearchCo-Recursive Semantic Self-Extension: A Mathematical Foundation for Open-Ended Intelligence
arXiv:2610.31097v2 Announce Type: replace Abstract: Artificial intelligence has advanced through scale, data, and computation, yet remains bounded by its representational framework. We ask what makes intelligence open-en…
- arXiv cs.AIresearchSolving Flood-It Puzzles: A Comparison of Tailored A* Search with Declarative Solver Approaches
arXiv:2610.31100v1 Announce Type: new Abstract: We present an optimized approach for finding minimal move sequences to solve Flood-It puzzles using A* search and compare it with approaches using SAT, Integer Programming,…
- arXiv cs.AIresearchDeepOpen: Decision-Oriented Intent Classification on BANKING77 and CLINC150
arXiv:2610.31104v2 Announce Type: replace Abstract: We present DeepOpen, a decision-Oriented intent-classification framework with dataset- specific systems for BANKING77 and CLINC150. On BANKING77, a single English class…
- arXiv cs.AIresearchConstraint Reasoning and Large Language Models Join Forces: Providing Contrastive Explanations for Real-World Optimisation-Based Applications
arXiv:2610.31119v1 Announce Type: new Abstract: We focus on optimisation-based Decision Support Systems in real-world applications. In this context, we aim to provide contrastive explanations that answer users' questions…
- arXiv cs.AIresearchSetCommit: Coordinated Token Commitments for Few-Step Diffusion Language Model Decoding
arXiv:2610.31120v1 Announce Type: new Abstract: Diffusion language models generate multiple token positions in parallel, but few-step decoding makes parallel commitment difficult: tokens that appear reliable individually…
- arXiv cs.AIresearchRethinking Fisher Vectors for Second-order Multi-scale Deep Feature Aggregation in Scalable Scene Retrieval
arXiv:2610.31146v1 Announce Type: new Abstract: Aggregating CNN responses into a compact discriminative vector, given their lack of geometric invariance, is a challenge. To address this challenge, we propose a codebook-f…
- arXiv cs.AIresearchDifferent Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models
arXiv:2610.31198v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) introduce unique quantization challenges due to their iterative denoising process. In this work, we reveal that quantization sensitivity is…
- arXiv cs.AIresearchTrion-1: Unifying Language, Protein Sequence, and Structure with Diffusion Language Models
arXiv:2610.31215v1 Announce Type: new Abstract: We envision a general-purpose protein foundation model as a unified, interactive model of sequence, structure, and function, capable of understanding, generation, and cross…
- arXiv cs.AIresearchReward-Weighted Preference Optimization for Selective Combinatorial Optimization Problems
arXiv:2610.31239v1 Announce Type: new Abstract: Reinforcement learning has emerged as an effective approach for combinatorial optimization, but most existing methods focus on problems such as the Travelling Salesperson P…
- arXiv cs.AIresearchReducing Multi-Horizon Photovoltaic Forecast Error through Tree-Anchored Expert Combination
arXiv:2610.31248v1 Announce Type: new Abstract: A strong direct tree model may remain the best standalone photovoltaic forecaster, yet a weighted combination can reduce its residual errors. We examine whether complementa…
- arXiv cs.AIresearchValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding
arXiv:2610.31338v1 Announce Type: new Abstract: Tree-based speculative decoding accelerates large language model inference by verifying multiple candidate branches in parallel. However, in practical serving scenarios, si…
- arXiv cs.AIresearchPhysTrace: Interpretable Temporal Evaluation of Physical Consistency in Video Generative Models
arXiv:2610.31429v1 Announce Type: new Abstract: World action models increasingly rely on pretrained video models assumed to capture physical dynamics for prediction, planning, and action generation. Existing evaluations…
- arXiv cs.AIresearchDIAL: Steerable Language Models with Distilled Instruction-Adherence Levels
arXiv:2610.31438v1 Announce Type: new Abstract: When a user says "Keep it short", how short should the LLM's response be? More generally, users and applications require different levels of instruction adherence, but prom…
- arXiv cs.AIresearchFairFRESH: A Neuro-Symbolic Framework for Fair and Explainable Household Food Recommendation
arXiv:2610.31506v1 Announce Type: new Abstract: Recommender systems typically serve one user at a time. However, in households, members share a finite pantry and follow different dietary rules, making independent recomme…
- arXiv cs.AIresearchFrom Prompt Rules to Golden Data Model: Production-Scale Generation of Personalized, Compliant Pharmaceutical Claims
arXiv:2610.31519v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate domain-specific commercial & medical content (e.g., claims, statements, and promotional phrases) in regulated…
- arXiv cs.AIresearchJev-DLC: Decision-Level Continual Learning from Typed Feedback
arXiv:2610.31521v1 Announce Type: new Abstract: Individual preferences often become visible only after deployment, when a user accepts one decision or revokes it in favor of another. Jev-style typed interfaces make this…
- arXiv cs.AIresearchBeyond Causal Masks: Auditing and Localizing Hidden Future-Token Leakage in Adaptive Sequence Models
arXiv:2610.31522v1 Announce Type: new Abstract: Hidden future-token leakage can create false architectural gains: an autoregressive model may appear substantially better under teacher-forced evaluation while its free-run…
- arXiv cs.AIresearchWhat Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models
arXiv:2610.31576v1 Announce Type: new Abstract: Masked diffusion language models generate tokens in parallel, but their efficiency depends on which predictions are committed. Learned unmasking policies improve the speed-…
- arXiv cs.AIresearchWho Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration
arXiv:2610.31579v1 Announce Type: new Abstract: Research on sycophancy asks whether large language models (LLMs) bend towards what their users want to hear. We ask the reverse question: when an LLM is confident, consiste…
- arXiv cs.AIresearchSimulated Control Evals
arXiv:2610.31593v1 Announce Type: new Abstract: Control evaluations measure whether safeguards can prevent an AI model from causing undesired outcomes even when it is intentionally trying to do so. These evaluations typi…
- arXiv cs.AIresearchDirect Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning
arXiv:2610.31667v1 Announce Type: new Abstract: Test-time scaling has emerged as a key inference strategy for reasoning models, where a model generates a large number of candidate solutions in the hope of finding at leas…
- arXiv cs.AIresearchV-JEPA 2 Meets AQA: Phase-Based Scoring and Reference-Based Feedback for Mountain Biking
arXiv:2610.30160v1 Announce Type: cross Abstract: We study mountain-bike action quality assessment (AQA) with weak labels and candidate feedback. The training corpus comprises 95 field-recorded jump clips with binary lab…
- arXiv cs.AIresearchFusionEval: Benchmarking Model Fusion for Large Language Models
arXiv:2610.30162v1 Announce Type: cross Abstract: Model fusion aims to integrate the capabilities of multi-expert models into a single model. Existing evaluations offer limited coverage of reasoning with long chains of t…
- arXiv cs.AIresearchGeoDiv KAN Solver for Time Fractional Navier Stokes Equations on Complex Domains to Realistic CFD Reconstruction
arXiv:2610.30179v2 Announce Type: replace-cross Abstract: Scientific machine learning provides a promising framework for solving complex problems in science and engineering. Notably, physics informed neural networks (PIN…
- arXiv cs.AIresearchDetecting AI Training in Datacentre Power
arXiv:2610.30182v1 Announce Type: cross Abstract: AI governance agreements require methods to detect large model training runs on a monitored computing cluster, without trusting the operator. We develop a method to detec…
- arXiv cs.AIresearchSelf-Evolving Static Analysis via LLM Pseudo-Labeling
arXiv:2610.30184v1 Announce Type: cross Abstract: Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules have not yet been written for the code in front of us…
- arXiv cs.AIresearchWhy Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT
arXiv:2610.30191v1 Announce Type: cross Abstract: Supervised fine-tuning adapts language models to specialized tasks but can disrupt previously acquired behavior. Existing approaches constrain parameters, gradients, or r…
- arXiv cs.AIresearchDetection Is Not Enough: Reasoning Traces as Testable Program Hypotheses
arXiv:2610.30200v1 Announce Type: cross Abstract: When a language model is deployed, no reference solution exists, so the reasoning trace it writes is the only evidence for judging its answer. The reference-free substitu…
- arXiv cs.AIresearchMPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
arXiv:2610.30202v1 Announce Type: cross Abstract: With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (PI) has emerged as a critical security threat. Att…
- arXiv cs.AIresearchMoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs
arXiv:2610.30206v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models scale model capacity efficiently by activating a small subset of parameters per token. However, in long-context inference, memory…