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 59
TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents
Terminal feedback in multi-turn agent training leaves both rollout allocation and local credit underdetermined.Advancing Clinical Trial Outcome Prediction with Domain-Specific Large Language Models
Clinical trial failures are a major barrier to efficient drug development, incurring substantial costs and delaying patient access to effective therapies.Simple Features Beat Most AI Control Monitors
AI control relies on monitors to catch a capable model that sabotages its work.Latent-Lens: Visual Perception in Small Language Models Through Latent Communication
Bridging independent vision-language models (VLMs) and small language models (SLMs) in a modular multi-agent system typically forces them to exchange information as discrete text, which creates a…Multimodal In-Context Learning with Explicit Rule Induction
A central challenge in multimodal in-context learning (MICL) arises from tasks that are ill-defined without context and require uncovering the underlying rules from demonstrations.Clinical-Protocol-Aware Cyber Resilience for Connected Clinical Technologies Under AI-Enabled Adversarial Conditions
Healthcare increasingly relies on connected medical devices, clinical information systems, cloud services, and distributed-care technologies, creating cybersecurity risks across clinical workflows.Different Models, Shared Failures: Auditing Frozen-Encoder Pools for Medical Segmentation
Average segmentation accuracy and model count do not reveal whether models fail on the same cases.Implicit Assumptions About Tasks in Continual Learning
Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once.Whose Values, Which Contexts, and What Signals? Grounding Cultural Value Alignment with Re3Culture
Cultural value alignment requires not only model optimization but also a well-specified target grounded in real-human evidence.Accurate and Auditable ECG Classification via Visibility Graph Neural Networks
Physicians read electrocardiograms (ECGs) from waveform shape and timing, yet accurate deep-learning classifiers rarely show which waveform regions drive their predictions.Backpropagation-free Deep Learning for Time-Series Classification
Deep neural networks for time series classification (TSC) are trained almost exclusively by error backpropagation, which imposes update locking and the weight-transport problem.RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces
Large closed-source reasoning models expose only their final answers.ReuScope: Auditing Data Reuse and Evaluation Sensitivity in Capsule Vision 2024
We develop ReuScope, a protocol for auditing data reuse and evaluation sensitivity, using Capsule Vision 2024 as a case study.Dynamical Memory Transformer: Selective Recurrent Memories with Constant Cost Attention
Transformers retain an explicit history of the sequence, allowing attention to directly retrieve past representations.SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI
Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation.Learning to Interact and Direct: Co-Evolving Video Director Agents
Video director agents orchestrate multistage production to realize users' creative visions.AI evaluators favor job applications written by certain AI models, independent of candidate quality
Job applicants increasingly use large language models (LLMs) to write cover letters, while employers deploy LLMs to screen them.Fuzzy selective state model for forecasting the dynamics of consumer preferences
We consider forecasting the dynamics of consumer preferences of retail chain customers.Automated Keyword Generation Using LLMs in a High-Volume Data Virtualization Service
In modern data infrastructure, a data virtualization service (DVS) allows users to create many versions of source datasets for different processing tasks.General-purpose foundation models surpass specialized ones on chemical property prediction tasks
Foundation models (FMs) learn reusable representations from large collections of unlabeled data.