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: 4,993 arXiv preprints and 7 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 15
Beyond the principle-practice gap: Responsible AI as situated epistemic and ethical practice
Responsible AI scholarship has found that ethical principles are frequently not reflected in AI design and development.Reasoning over Non-Parametric Memory in Multilingual LLMs: A Cognitive-Based Analysis of Relational Knowledge
Retrieval-augmented generation (RAG) assumes that language models can reason over relations stated in their context rather than fall back on associations memorized during pretraining.Dexterous Robotic Hands in the Foundation-Model Era: A Full-Stack Survey of Hardware, Data, Cross-Embodiment Transfer, Learning, and Evaluation
Dexterous robotic hands are increasingly coupled to large-scale human data and foundation models, yet progress in hardware, representation learning and evaluation is often assessed separately.ConceptARC at Scale: Studying Conceptual Understanding in Reasoning Models
Large reasoning models (LRMs) perform well on challenging benchmarks, yet it remains unclear whether they form generalizable abstractions across conceptually related reasoning tasks.Smartphone-Aided VR Exergames for HIIT: Gamifying Fitness with Real-Time Pose Estimation
This paper introduces an innovative virtual reality (VR) exergame system designed to gamify High-Intensity Interval Training (HIIT) workouts through 11 predefined combo moves, including squat-punch…TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing
Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift.EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models
Generative video models are increasingly used as visual world simulators, yet their primary strength lies in rendering plausible pixels rather than reasoning about how a world should evolve.Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces
Scientific image-analysis workflows require agents to select among diverse capabilities like description, detection, counting, and segmentation.FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning
One-shot and few-round federated learning (FL) reduce communication burden by constructing a global model within one or a few communication rounds, but often achieve lower performance than…Transforming Integer Grids to Spatial Intuition: Perception, Not Planning, Governs ARC-AGI-3
Sample-efficient fluid intelligence requires agents that rapidly form working models of unfamiliar interactive environments.Message-passing graph persistence
Message-passing graph neural networks (GNNs) are limited in expressive power by the one-dimensional Weisfeiler-Leman test.Task-Efficient Agent Evaluation Using Cached Traces
Efficient benchmarking estimates a system's full benchmark performance from a small number of task executions.Rules, Traces and Routing Statistics: Training and Calibration Data for Open Models on ARC-AGI-2
We study which training and calibration data help three open models solve ARC-AGI-2 tasks when the solver runs offline on four L4 GPUs for at most 12 hours.Enabling AWS Cloud FPGA Development Using High-Level Vitis HLS
We present a toolchain for development of ML models on AWS EC2 F2 cloud FPGA infrastructure from high-level language, implementing a complete Vitis HLS to HDK bridge to AFI workflow that has been…Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token
Under stochastic decoding, a single context can elicit many different answers from a language model.ServerBench: How can your coding agents design specialized LLM serving systems?
Large language model (LLM) coding agents develop software through experimentation, offering an opportunity to design the serving systems supporting their own operation.CompressionBench: How can your coding agents compress LLMs?
Recursive self-improvement requires AI systems to improve the models and infrastructure used by subsequent systems.CounterFactual Retrieval for Evidence-Aware Individual Animal Identification
Automated identification of individual animals is moving from small curated studies toward shared benchmarks and reusable foundation models.On Turn-Level Best-of-N Sampling for Scaling LLM Agents
In this work, we evaluate a simple inference-time scaling approach based on \textit{turn-level best-of-N sampling} (\method) for large language model (LLM) agents on complex, long-horizon tasks.Learning to Decode Linear Codes with Generalized Belief Propagation Network
Error correcting codes are a fundamental component of communication systems, enabling reliable data transmission over noisy channels.