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 12 October 2026 to 6 November 2026: 4,992 arXiv preprints and 8 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 239
A Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization
Domain-specific curvature is an appealing idea for domain generalization (DG), but curvature learning can denote substantially different computations.Holding Agents Accountable with Verifiable Agent Insurance
While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data.Consider, Then Choose: Order-Invariant Decisions in System One Models
System One models answer typed questions in a single forward pass and promise the same answer for the same input.Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory
Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements.Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision.LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed tomography (NCCT) is increasingly used for opportunistic screening because of its low cost and…FALLNEST: Dual-Domain Dataset Condensation of Imbalanced IMU Data for Wearable Fall Detection
Wearable fall detection is hampered by rare fall events, scarce labeled IMU data, and the cost of training deep models on large, imbalanced corpora.Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Third-party skills can expose LLM agents to malicious instructions hidden by encoding.JevGPT: Thinking Fast and Slow in Autonomous Research
Autonomous research agents must acquire and reason over evidence within a limited budget.Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller
Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent training.Output Discipline Sets the Floor: A Falsification-Guided, Model-Agnostic Agent Protocol for Auditable Hypothesis-Driven Decision Making
What binds large language models on auditable, hypothesis-driven decision tasks, where every candidate can be checked against the evidence?A dataset of formalised theorem statements from the Annals of Mathematics
Recent progress in autoformalisation of mathematics using AI has been impressive.Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction
Guardrail approaches that rely on reasoning-based large language models (LLM) improve safety decisions, but come with substantial inference overhead due to the explicit reasoning.AffectWorld: Benchmarking Emotion-Driven Future World Prediction
The world encompasses both physical environments and human actors.SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems
Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation.Complex materials engineering via Provenance Action Graphs: potential, structure and demonstration
This work discusses and tests the potential of reaction graphs for material synthesis, in which events consist of reaction steps (actions) and their outputs (observations).ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On
Virtual footwear try-on (VFTON), a critical yet underexplored area in virtual try-on (VTON), aims to synthesize faithful try-on results given diverse footwear and model images while maintaining 3D…AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents
Training business automation agents requires executable tasks that connect a natural-language request to an application state and a verifiable end state.Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and English
Post-training quantisation reduces the memory cost of large language models, but it remains unclear whether compression preserves language skills of regional varieties as reliably as their…Let the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation
A robot following a multi-step instruction needs to act on the right objects in the right order, even as the scene changes.