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 12 October 2026 to 6 November 2026: 4,992 arXiv preprints and 8 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 231
From Events to Reasoning: Hierarchical Rule Composition over Explicit States
What a reasoning system emits is a conclusion; what it owes is a justification.Towards Adaptive and Real-Survey-Aligned Simulated Urban Mobility Behaviour of Generative Agents
In existing agent-based simulations of multimodal urban mobility, agents, representing humans, choose their travel modes either using discrete choice or machine learning models fitted on structured…ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation
Long-horizon GUI agents rely on visual history to maintain task states, but retaining historical screenshots increases visual-token usage and inference costs, while textual summaries can discard…From Individual Songs to Music Corpora: Evaluating Explainable Harmonic Decision-Making on HookTheory
Automatic melody harmonization is often evaluated through individual compositions or data-driven corpus models.RL Teaches VLMs Where to Attend but Not How to Perceive
Although reinforcement learning (RL) effectively trains Vision-Language Model (VLM) agents, the mechanisms behind these capability gains are poorly understood.From Detection to Decision: Calibration and Deferral for Prompt-Injection Detection
Prompt-injection defenses are commonly evaluated as binary detectors, although deployed LLM applications must make operational decisions about whether to allow, block, or escalate potentially…Foundation Models for Event Prediction Across Heterogeneous Event Logs
Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational systems.YUBI-Real2Sim: 3DGS Scene Verification for Reliable Policy Evaluation
Evaluating VLA policies on real robots is costly, time-consuming, and difficult to reproduce, making real-to-sim simulation essential for scalable evaluation.Enhanced Detective: A Dual-Stage Proactive Defense Against Internal Poisoning Attacks in Financial Fraud Detection Using Federated Learning
With recent developments in Artificial Intelligence (AI), the adoption of distributed learning paradigms such as Federated Learning (FL) has emerged.Box-WAM: Box Trajectories as Compact State Representations for World Action Models
World action models (WAMs) are a category of policy models that ex- plicitly predict both actions and future world states.Towards Green AI: Evaluating Energy Efficiency for Quantized LLM Inference
While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting impact on energy usage and carbon intensity are…TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency
Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasoning text must wait for autoregressive decoding.Convex-Analytic View of Query Selection for Safety Verification of Markov Decision Processes
Safety verification of a Markov decision process (MDP) asks whether the probabilities of reaching several failure states jointly lie in a convex safe region under every scheduler.Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents
Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one.Reference Wording Shapes Retrieval of Robot Task Instructions
Identifying a robot task from a short instruction is sensitive to which descriptions are available for retrieval.FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation.Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols.Dissociating Answerability from Extraction in LLM Question Answering over Radiology Reports
Answering questions from radiology reports involves two decisions: whether the report contains an answer and which span gives it.Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification
Entities in real-world systems often evolve over time: users shift between information consumption patterns, researchers migrate between fields, and firms transition between financial risk states.RAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control
Operational mobile networks are rich in observations but poor in interventions: they continuously generate large volumes of passive telemetry, while controlled action--response trajectories remain…