AI & Machine Learning · Computer Science & AI
Artificial Intelligence
The newest papers in Artificial Intelligence that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 11 October 2026 to 5 November 2026: 4,998 arXiv preprints and 2 OpenAlex records.
Get the few papers worth your time in Artificial Intelligence every morning.
Follow Artificial Intelligence and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 63
LF-VideoQA: Evaluating Long-Video Understanding with Long-Form Theory-of-Mind Questions
The hardest part of understanding a long video is not pinpointing any one moment but synthesizing many, e.g., answering a question that requires tracking what develops across hours of content and…Agent Stack for ML Training Lifecycle: Generation, Validation, and Optimization
Production model development requires repeated architecture design, platform integration, debugging, training, and evaluation.Dependence-Aware Risk Assessment and Optimal Design of AI-Agent Safeguard Systems
Large language model (LLM) agents increasingly rely on safeguards to prevent unauthorized actions while preserving legitimate service.Geometric and algebraic inference in humans and neural networks
Humans possess a remarkable ability to draw inferences from limited data.CalVLA: Shaping Native Confidence in Vision-Language-Action Policies with Outcome Supervision
Can a vision-language-action (VLA) policy signal likely task failure from its own action probabilities?Behavior Graphs: Unsupervised Graph Structures for Interpreting Robot Deployment Data
Data flywheels promise continuous improvement via insights from deployment data.Hacking or Just Failing? A More Capable LLM Monitor Better Separates Reward Hacking from Honest Failure
An agent's visible score can exceed its real progress because it gamed the score or because it simply made mistakes, so a useful reward-hacking monitor must tell the two apart.On the Framing Effect of AI Red-Teaming Instructions: Evidence from Prior Exercises and Controlled Simulations
AI red-teaming, adversarially probing generative AI systems to surface harms, has become a central evaluation method.Nonconformal Distortion and Local Orientation Reversal in the Fourier Circuit of a Modular-Addition Transformer
We study the local differential geometry of a Fourier-based modular-addition circuit in a one-layer transformer whose algorithm has previously been reverse-engineered.A Spectral Renormalization-Group View of Learning
We study how the layers in deep neural networks (NNs) converge, using Wilsonian Renormalization-Group (RG) ideas to organize the spectral picture.Online Fair Division of Chores with Upgrade Recourse
We study the online fair division of indivisible chores among $n$ agents under upgrade recourse, where earlier assignments may be revised but each chore previously assigned to an agent must be…OmniMechanism Design for Human-AI Collaboration with Impressionable Minds
As AI systems are increasingly deployed in high-stakes domains such as healthcare, effectively integrating human expertise with AI outputs is critical for reliable decision-making.Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent
When a multi-turn agent delivers a tool's structured records into the model's context and re-emits them each turn, every turn can corrupt data the tool computed correctly.Analog and hybrid computing in the 21st century
Analog computers solve problems through physical representations of mathematical variables and relations, often using the dynamics of electronic circuits and their associated signals.Quantiles, Not Points: Streaming Quantile Matching for Ordinal-Aware LLM-as-a-Judge Calibration
LLM-as-a-judge scores are often distributionally shifted from human ratings on any given evaluation task, and post-hoc calibration (mapping LLM to human scores in a small labeled anchor set) has…Learning to evolve by matching velocities
Learning the continuous-time evolution of nonlinear dynamical systems relies on trajectory-based objectives, which require simulating the learned dynamics during training and backpropagating through…From Lookups to Lessons: Turning Retrieved Knowledge into Parametric Memory
Retrieval-augmented generation (RAG) helps large language models (LLMs) answer factual questions beyond their training data, but it adds storage and inference costs.From Small to Large: Assessing Medical Reasoning, Benchmark Contamination, and Model Size in Language Models
Large language models (LLMs) now answer medical exam questions at or above expert level, but it is unclear whether such scores reflect clinical competence, or are instead affected by the format of…Exo: An Architecture for Self-Improving Systems at Runtime
Agent harnesses govern how language models act in an environment; designing their policies by hand is difficult, while automated techniques require representative datasets and costly executions.Compression Technique Interactions in Small Language Models: A Factorial Ablation Study
Deploying small language models on resource-constrained hardware requires compression, yet practitioners lack systematic guidance on how quantization, pruning, and post-compression recovery interact…