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 115
RoboReason: Boosting Robotics-Relevant VLM Reasoning Through Scalable Data Generation
Vision-Language Models (VLMs) have demonstrated impressive performance when integrated into robot manipulation pipelines, but real-world evaluation of VLM capabilities on downstream robotics tasks…Unlocking the Specialization Capability of PPG Foundation Models for Wearable Signals through Structured Pruning and Adaptive Fine-Tuning
Photoplethysmography (PPG) plays a central role in wearable health monitoring and clinical decision support.One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation
Deploying a language-guided navigation policy in a new building usually means watching it fail.Are We Done with UMLS Injection into Language Models for Medical Question Answering?
Maybe not.ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models
Feed-forward 3D foundation models have recently reshaped multi-view reconstruction, yet dynamic 4D understanding still often relies on large-scale motion supervision or hand-crafted…Beyond Static Structures: Linking Protein Dynamics to Function via DynaReason-Pro
Intrinsically disordered proteins (IDPs) carry out their functions through heterogeneous conformational ensembles that reflect their dynamics, yet most protein function prediction methods rely on…Rectified Language Flow
Continuous-state flow and diffusion models offer a promising approach to fast, parallel language generation, but matching the generation quality of autoregressive models remains challenging.Memory or a Clock? Auditing a Memory Advantage in XLand-MiniGrid with Seeds, Maps and Evaluation Noise Apart
On a partially observable XLand-MiniGrid task, an LSTM agent beats a memory-free MLP by 25 percentage points.EnvLunch: The Environment as a Free Lunch for Learning to Interact
For agentic data analysis, language-model agents often require a large number of annotated tasks to learn how to interact effectively with executable environments (i.e., databases).Learning What to Share: Expert Specialization for Time-Series Forecasting
A central challenge in multivariate forecasting is deciding what to share across channels and where to specialize.Adapting DNNs to Embrace Voltage Scaling Induced Errors via Accumulation-Aware Quantization
The pervasive deployment of Deep Neural Networks (DNNs) across the computing spectrum has brought growing attention to energy efficiency, alongside raw performance.EEGBiFormer: Real-Time EEG Attention Classification via Hybrid CNN-Transformer with EEG-Informed Auditory Protocol Validation
Sustained attention is critical for academic performance, yet existing auditory support tools are static and not grounded in real-time neural evidence.Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players
Can LLM agents carry a hard real-world problem from raw data to a system that holds its own against people?Numina Fuse: Interactive Autoformalization in Lean 4
Numina Fuse is an agent-native application for formalizing mathematics in Lean 4.ReGE: Stronger Agents through Experience Synthesis
Repeated attempts at interactive tasks uncover facts, useful operations, and failures that can inform subsequent execution.FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs
Many agent tasks recur with new data or small changes, yet agents regenerate their reasoning and actions on each run, producing different results.Intervention-Certified Amplification: A Validity Gate for $σ$-Weighted Post-Training
Hybrid post-training often mixes supervised fine-tuning (SFT) and reinforcement learning (RL), using training-side signals to set each sample's balance.Counterfactual Test-Time Augmentation for Shortcut Removal in Language Models
Large language models (LLMs) can exploit shortcuts, i.e., correlations present in training data that may not hold at test time.OS-Wizard: Scaling Computer-Using Agents to Specialized Software via Knowledge-Guided Exploration
Computer-using agents are increasingly capable of performing complex tasks in the digital world.Rank-1 Weight-Corrected Trainable Weight Averaging for Out-of-Distribution Detection
Out-of-distribution (OOD) detection identifies inputs outside the training distribution.