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 97
ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning
Reasoning language models generate thousands of tokens per answer, and generation speed is limited by memory bandwidth, so storing weights in two bits instead of bfloat16 can potentially make…NumTrace: Auditing the Number Provenance of Financial Analyst Agents
A numerical claim generated by a financial analyst agent can match a number in a company filing but refer to the wrong entity, concept, period, unit or scope.AIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment
Deploying and optimizing a PyTorch inference project on a dedicated accelerator, especially an on-device NPU, requires more than using a framework device API as with CUDA.LE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation
Training-free few-shot adaptation of vision-language models typically constructs a classifier from CLIP's final projected image representation, leaving intermediate representations unused.Waypoint: Analytically Modeling GEMM for CPUs
High-performance General Matrix Multiplication (GEMM) implementations rely on breaking down GEMM into carefully selected tiles to achieve peak performance.PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds
Physical reasoning underpins how embodied systems understand and act in the physical world, yet vision-language models (VLMs) remain unreliable on questions about dynamics and physical causality.How Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation
Coding agents can adapt their harnesses, the software, configuration, and instructions used to run them, based on experience from earlier tasks, but whether these adaptations improve their behavior…Stop or Clarify? Experience-Conditioned Active Fact Verification
Fact-verification benchmarks score the final label, while an interactive verifier must first decide whether the available evidence is sufficient.Reasoning Patterns for Efficient AI Coding: An Empirical Study
Large Reasoning Models (LRMs) generate long reasoning traces that expose intermediate inference behavior, offering opportunities to study and control reasoning in AI coding.Relational Composition as Parallel Transport: What Per-Entity Frames Force in Attention
A dot product means something only when both vectors share a coordinate system.Correlation-Aware Exploration for Long-Trace Reasoning
Reasoning models trained with Group Relative Policy Optimization (GRPO) now produce chains of thought thousands of tokens long, and recent studies reveal that such training is prone to policy…Decision Model Factory: Building Specialized Sovereign Decision Models
Decision needs vary with each application, language, and deployment environment.GUIFlow: Temporal Redundancy-Aware Incremental Inference for GUI Agents
GUI agents built on vision-language models interact with continuously evolving interfaces, yet conventional inference repeatedly recomputes representations of largely overlapping observations and…C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails
Despite the remarkable capabilities of large language models (LLMs) across diverse applications, they remain vulnerable to generating content that violates safety regulations and policies.The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming
Automatic red teaming increasingly relies on large language models (LLMs) to iteratively diagnose failed attacks and propose improved adversarial prompts or injections.SVD-Attention: Efficiently Analyzing Attention Blocks in Transformers
Pretrained transformers spend a large share of their inference compute inside self-attention, yet the per-head query-key interaction is structurally low-rank by construction.Sparse Recovery Bird's-Eye View Model Soup for Robust Camera-Based 3D Object Detection
Camera-based bird's-eye view (BEV) perception methods such as Fast-BEV have demonstrated promising results with fast inference speed and competitive accuracy.AskGLP1: A Knowledge Graph LLM Agent for Exploring GLP-1 Experience from Online Patient Narratives
GLP-1 medications are increasingly used for weight management, and many people share their experiences online.Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention
Modern large language models (LLMs) often exhibit overconfident errors, assigning high confidence to incorrect predictions and thereby undermining reliability in real-world use.Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery
Deep narrative understanding requires distinguishing what happens from how it is presented, moving beyond the chronological fabula to decode the sjuzet, the discursive organization through which…