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 41
When Model Complexity Matters in Cross-Subject Naturalistic fMRI Prediction
Increasingly complex neural models predict blood-oxygen-level-dependent (BOLD) responses to naturalistic stimuli, but the predictive value of this added complexity remains unclear.Exploit or conform? How norm utility prompting changes the way LLMs use community beliefs
Large Language Models (LLMs) serve both as tools for aiding human decision-making in everyday life and as models of human agents in experimental simulation studies.Forgetting to Improve: Principled Data Removal in Active Learning
The uncertainty of a statistical model is most commonly factorized into an aleatoric and an epistemic part.HybridSpec: Throughput-Aware Speculative Decoding for Hybrid GDN-MoE Models
In speculative decoding, parallel drafters such as DFlash make drafting cheap, so target verification dominates each round.Look Before You Launch: Learned Throughput Prediction for Hardware Selection in a Production Training Fleet
In mixed-vendor accelerator fleets, many training jobs can run on several hardware types, and the best choice depends on each job's throughput on each type.Query-based Submodular Data Selection for Efficient Instruction Tuning
As large language models are fine-tuned for increasingly specialized tasks, their performance depends more on which training examples are selected than on how many.On the Primacy Bias in RLVR Training
Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a promising approach for enhancing the reasoning capabilities of large language models.AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance
Real-world problems span diverse domains, including program synthesis, symbolic reasoning, planning, and optimization, and often require fundamentally different solution paradigms.ScienceVision: Can AI Observe and Reason Like a Scientist?
Scientific discovery builds on accurate observations interpreted through domain knowledge and reasoning.CAST-Bench: Tracing Every Sound to Its Source in Multi-Shot Audio-Video Generation
Existing benchmarks for joint text-to-audio-video (T2AV) generation evaluate perceptual quality and audiovisual alignment, but balanced sound-source sam?pling and separate reporting by shot…LLM-based NPCs in Video Games: A Systematic Mapping Study
For decades, non-player characters (NPCs) have been driven by rule-based systems whose personalities and interactions are scripted before release.A Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI Development
Large Language Models (LLMs) exhibit powerful code generation abilities, fostering agentic systems to automate edge AI application development.Toward Executable Multi-framework Front-end Code Generation with Self-Correction
Generating codes from UI screenshots has recently benefited from MLLMs, yet existing methods centered on HTML targets and transfer poorly to multi-frameworks such as React, Vue, and Angular.Learning by Doing: Autonomously Compiling and Curating Agent Skills from Verified Traces
Memory systems for production LLM agents mostly store semantic memory (facts about users and domains) or episodic memory (earlier interactions).Vocabulary Aligned Explanations for Computer Vision Models
Optimizing vision models for accuracy does not force the model to learn and utilize human-understandable and domain-specific concepts and rules.ERIA: An Instruction-Optimized Agent for Clinical EEG Reporting
Clinical EEG interpretation requires integrating technical quality, background and behavioral states, interictal and ictal abnormalities, and overall clinical context across long recordings.FOCUS: Closed-Loop Attention Feedback for Efficient Vision-Language Understanding
Processing every video frame through Vision-Language Models (VLMs) adds significant inference cost and limits their ability to comprehend real-time video.I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents
Large language models are increasingly capable of writing and executing code, suggesting a natural paradigm for tool-augmented agents: expressing tool use as programs rather than isolated calls.CONFIRM: Governing Scientific Reporting for Trustworthy Agentic Neuroimaging
Large language model (LLM) agents can autonomously run neuroimaging analyses from research questions to reported findings.Can Large Language Model Agents Learn by Watching Tutorial Videos?
Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that understanding into future tasks.