AI & Machine Learning · Computer Science & AI
Machine Learning
The newest papers in Machine Learning 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 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Machine Learning every morning.
Follow Machine Learning 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 175
Integrable building blocks for symplectic neural networks: learned-type layers, fiber-preserving layers, and what a single layer can do
Exactly symplectic neural networks are built almost exclusively from shear maps and gain expressivity only through depth.Beyond the Teacher: Understanding and Preserving Distillation Overshoot in Agentic On-Policy Distillation
On-policy distillation (OPD) trains agents on their own trajectories using supervision from a stronger teacher.Normalizing Flow for Neural-Enhanced Track-Before-Detect
Multiobject tracking (MOT) is a fundamental capability in autonomous navigation, radar and sonar systems, as well as 6G integrated sensing-and-communication (ISAC) networks.PACT: NVFP4 Data-Flow LoRA Fine-Tuning on Consumer GPUs
Fine-tuning language models on consumer GPUs is constrained by computation and memory.HCFM: Helmholtz Component Flow Matching for Time Series Anomaly Detection
Flow Matching (FM) is an efficient simulation-free approach for training flow-based generative models, making it a promising foundation for scalable time-series anomaly detection (TSAD).Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On
A guardrail classifier is reported as if unsafe were a property of text.The Optimal Sample Complexity of Pointwise Replicable Agnostic Learning
Pointwise replicability asks that two independently trained predictors, using the same random seed, agree at each fixed query with high probability.Auto-MD-bench: Evaluating Autoresearch Agents for Real-World Medical Tasks
Autonomous agents are increasingly capable of developing machine learning (ML) models end to end.CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?
Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabilities.Conformal Prediction-Enabled Sequence-level Policy Optimization for Reasoning Language Models
Reinforcement learning improves the reasoning capability of large language models through verifiable rewards for mathematical and coding tasks.Non-Acceleration of the Heavy-Ball Method in 1D
Despite having an asymptotically optimal rate of convergence on convex quadratics, the acceleration of Polyak's heavy-ball method and a characterization of its dynamics within more general settings…Self-organizing reinforcement learning: a learner-free swarm approaches the explore-exploit optimum
The explore/exploit trade-off is the core problem of reinforcement learning (RL).Compile Once, Run Cheap: Frozen, Portable Skills for Embodied Agents, and What Recursive Self-Improvement Adds
Embodied AI lacks the data-rich pretraining that gave language models their agents and skills, so new manipulation capability costs demonstrations per task or a frontier model in every episode.Polynomial Learning of Positive ReLU Networks under Gaussian Inputs
We study positive, bias-free, one-hidden-layer ReLU networks under standard Gaussian inputs.Memory as Belief: Bayesian Evolution of Memory for Self-Evolving LLM Agents
Large language model (LLM) agents increasingly rely on external memory to accumulate past experiences for continual adaptation.ClinSDT: LLM-Encoded Clinical Semantic Guidance for Sepsis Treatment via Decision Transformer
Offline sepsis treatment aims to learn treatment policies from retrospective ICU trajectories.Trackable Skill Library Lifecycle Management for Agentic Reinforcement Learning
Skill-augmented agentic RL has emerged as an effective approach to improving LLM agents on long-horizon tasks.Decision-Target Reversal under Informative Label Missingness
Informative label missingness can improve classification efficiency because the pattern of label availability may itself contain information about the discriminant structure.Many Repairs, One Direction: Steering Code Models Toward Safer Cryptographic API Use
Cryptographic API misuse in large language model-generated code can compromise software security.TIRE: Top-Down Formula Instantiation with Reliable Execution for Physics Problem Synthesis
Advancing physics reasoning in large language models requires scalable training data that connect physical laws, concrete problem scenarios, and verifiable numerical answers.