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 78
CHORD: Cross-Model Hallucination Detection via Relational Graph Discrimination
Hallucination detection is critical for deploying large language models (LLMs) in real-world applications.LLM-PowerTrace: A Dataset of Time-Resolved GPU Power Traces for AI Compute
AI compute is becoming large and fast-changing electrical loads.What Should a Navigator Remember? Spatiotemporal Memory for Zero-Shot Vision-Language Navigation
Zero-shot vision-and-language navigation (VLN) requires an agent to use past observations without navigation-specific training.Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors
Extremely sparse-view computed tomography (xSV-CT) is critical when scanning time, motion, or radiation tolerance limits each scan to only a few projections.Can LLMs Faithfully Solve Ontology Engineering Tasks? A Mechanistic Interpretability Study
Ontological knowledge underpins large language model (LLM) performance on knowledge-intensive tasks.A Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI Accelerator
Frontier large language models write correct CUDA kernels for most single-operator benchmark tasks, yet their accuracy collapses on accelerators whose architecture and programming language they have…MUSE: Multi-Level Memory with Selective Runtime Injection for Scientific Coding Agents
Historical experience can guide scientific coding at multiple levels, but task-level retrieval may miss implementation lessons that become relevant during execution.Statutory Article Retrieval from Arabic Judicial Narratives: Family Law and Law of Evidence in Saudi Arabia
Reliable legal information retrieval must ground legal reasoning in authoritative statutory sources.Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes.Aligning Misaligned Benchmarks for Single-View Novel View Synthesis
While single-view novel view synthesis methods have been dramatically enhanced recently, how to quantify their performance has yet to be standardized.WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video
Producing long-form videos from narration requires interdependent decisions that remain coherent across shots.Encode Once, Answer Many: Internalizing Context via Parametric Flow
Large language models are typically adapted to a task either by placing knowledge in the input context, which keeps it external and re-encodes it on every call, or by fine-tuning, which internalizes…SparseTokenGS: Gaussian-based Sparse-View CBCT Reconstruction via Reusable Token Pool
Sparse-view cone-beam computed tomography is widely used for fast, low-dose volumetric imaging and lesion localization in dentistry and image-guided interventions, but it introduces severe artifacts.Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation
The external sources retained in our non-systematic audit did not isolate the incremental security or utility effect of consuming /llms.txt while ordinary retrieval remained fixed.Compute Has Shape: Self-Morphing the Internal Computation of Frozen LLMs
Test-time scaling improves large language models through additional computation, but how to adapt the topology of internal computation to individual inputs remains underexplored.SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning
Outcome-based reinforcement learning provides coarse supervision for long-horizon LLM agents: failed trajectories may contain correct steps, while successful trajectories can contain errors.Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents
Self-improving LLM agents edit their own harness, the prompts and rules around a fixed model, and keep an edit only if an acceptance gate scores it higher on a batch of tasks.Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web
The Agentic Web needs to support continuous collaboration among agents from different organizations.LLMs as Judges and Examinees for Medical Item Difficulty Prediction
Predicting medical item difficulty from item text alone remains challenging.SpaceAct: Benchmarking 3D Spatial and Temporal Reasoning via Closed-Loop Action and Active Perception
To solve problems in 3D space rather than merely describe images, multimodal large language models (MLLMs) need 3D spatiotemporal reasoning: reconstructing 3D geometry from occluded 2D views…