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 163
NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
Catastrophic forgetting is a central obstacle in single-stage fine-tuning of large language models (LLMs) on a new task, especially when the original pretraining data are unavailable.Which Answers Agree? Evaluating Self-Consistency from Incomplete Logs
Self-consistency answers a question by generating multiple responses and selecting the most frequent answer.Remember Less, Adapt Longer: Bounded-State In-Context Reinforcement Learning with Recurrent Summary Memory
In-context reinforcement learning (ICRL) enables agents to adapt to new tasks without parameter updates, relying on memory to retain what they learn from experience.Computation, Not Memory: Chain-of-Thought and State Tracking in LLM Agents
Language-model agents often reason before they act, and the value of monitoring that reasoning depends on how it relates to their actions.Detection Augmented Learning In Non-Stationary Bandit Environments
We study the problem of non-stationary bandits without knowledge of the environmental changes.SAR: Learning Global Item-Space Matching and Geometry-Aware Placement Ranking for Buffered Online 3D Bin Packing
Online 3D bin packing with a bounded buffer requires irreversible item-selection and placement decisions under limited knowledge of future arrivals.Fair Regression under Approximate Demographic Parity
Exact demographic parity requires the same prediction distribution across sensitive groups.Sector-Ring Linear Reservoirs: Sector-Wise Decay-Timescale Allocation With State Reuse Across Candidate Settings
In reservoir computing, performance depends on whether the fixed dynamics of the reservoir suit the task, and the appropriate memory length and frequency response differ across tasks.Communication-Efficient Federated Domain Generalization in Edge Networks via Dynamic Prototype Regulation
Federated learning (FL) is a distributed paradigm for Internet of Things (IoT) edge networks.Is it RL or Data? A Controlled Comparison of GRPO and Rejection-Sampling Fine-Tuning
Bauer et al. (2026) showed that in low-data reinforcement learning with verifiable rewards, training GRPO on mixed-difficulty prompts gives up to 5x the sample efficiency of easy-only prompts.Diffusion Language Models Change Speed Across Tasks and Languages
Diffusion language models can write several tokens in one forward pass, and they decide during generation how many passes to spend.SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation
Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost.Measurement Validity and Representation Dynamics of Confidence Signals in Large Language Models
Whether a language model "knows what it knows" matters for trustworthy deployment and for deciding when it should abstain.ACE-Trader: Adversarial Co-Evolution for Generator-Critic Trading Systems
Generator--critic trading systems pair an LLM-based trader that makes trading decisions with a red team agent that evaluates these decisions and provides feedback for revision.Rubrics Beyond Evaluation: Exploiting Rubric Structure in Reinforcement Learning
Rubrics are widely used to evaluate open-ended question answering by breaking overall quality into explicit criteria.Statistical Learning Theory for Direct Preference Optimization
Direct Preference Optimization (DPO) learns from pairwise preferences through a logistic objective whose score-difference parameterization follows the Bradley--Terry model.Are Self-Evolving Agents Continual Learners?
Large language model agents are often deployed in environments where new knowledge, tools, and workflows keep arriving.Adaptive Decoding Methods for Token-Efficient Reinforcement Learning
Rollout decoding affects both which trajectories are used for reinforcement learning with verifiable rewards (RLVR) and how many completion tokens are spent collecting them.CODA: Cohort- and Drift-aware Foundation Model for Multimodal Clinical Reasoning
Recent advances in multimodal foundation models have demonstrated strong performance across diverse clinical tasks.Residual-Guided Adaptive Tucker Rank Allocation for Parameter-Efficient MCI Conversion Prediction
Allocating limited trainable capacity across convolutional layers is a central challenge in parameter-efficient fine-tuning (PEFT) of pretrained three-dimensional (3D) networks.