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 237
ChampionKV: Head-Wise Adaptive Budget Allocation for KV Cache Compression
Some observation-window-based KV cache compressors use prompt attention to identify important tokens but allocate uniform or predefined budgets across heads, overlooking input-dependent differences…Can Machine Learning Potentials Be More Accurate Than the Methods They Are Trained On?
Although machine learning potentials (MLPs) generalize across configurational and chemical compound spaces, their accuracy is commonly believed to be limited by their training methods, with…Scaling Vision Transformers Without Training: Prune-and-Merge Token Compression
Vision Transformers achieve strong performance but incur high computational costs from quadratic token interactions.High-fidelity Three-Dimensional Flow Field Reconstruction Driven by Turbulent Fluid Dynamics
High-fidelity three-dimensional turbulent flow fields are essential for scientific and engineering analyses, yet obtaining them through direct numerical simulation or high-resolution measurements…Beyond Black Boxes: Visual Grounding for Text Embeddings
In this paper, our goal is to represent text embeddings as sketches for three main reasons.inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs
This work investigates the application of the Membership Inference Test (MINT) to large language models (LLMs) fine-tuned with LoRA, aiming to determine whether specific samples were used during…Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents
Long-term memory has become a core component of large language model (LLM) agents.From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning
Transformers can implement reinforcement-learning algorithms in context, yet how off-policy control emerges within Transformers remains poorly understood.Uncertainty Evaluation: Bridging Machine Learning and Measurement Science
Reliable uncertainty evaluation is essential for assessing the trustworthiness of machine learning (ML) predictions, particularly in safety-critical applications.WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
Scaling interactive environments is important for training long-horizon agents through reinforcement learning.AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement
Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives.ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch
Autoresearch systems increasingly undertake entire research projects.One-Sided Verification Under Limited Expert Review
AI has become increasingly helpful in scientific discovery, yet human expert review remains essential for those problems without reliable automated evaluation, posing a fundamental challenge as…AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses
Ambiguous or incomplete task specifications complicate both execution and clarification for language-model agents.LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity
Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis.CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks.APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions.Chain of Thought Monitoring Can Fail Even When CoT Is Necessary
Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems.A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge
Large language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a scalable alternative when human evaluation is too…When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features
Graph Neural Networks (GNNs) commonly assume that node features are fully observed, despite missing features being pervasive in real-world applications.