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 119
Representation Learning via Composite Subspace Flow Matching
Distilling semantic meaning from raw image data remains a challenge in machine learning.MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports
Although Large Language Models (LLMs) have demonstrated potential in clinical documentation, generating the rigorous, evidence-based reasoning required for unprecedented, atypical, and rare disease…Heterogeneous Space Data Centers: A Key Paradigm for Future Non-Terrestrial and In-Orbit Services
Lower space-launch cost and advances in AI are driving space-based data centers (SDCs) that provide AI-centric computing and communication services to in-orbit and non-terrestrial assets.Beyond Pattern Matching in 3D MLLMs: Part-Level Functional Reasoning for Generalizable Recognition
3D MLLMs recognize objects via pattern matching, which fails when geometrically similar objects require functional reasoning to disambiguate (e.g., dresser vs. wardrobe).Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs
Finding which phenomena occur in a tokamak discharge, and when, is often a manual task."Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs
Negation occurs in every language, yet its surface realization differs drastically.Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation.Complementing DINO Features with Image Structure for Part Discovery
Self-supervised Vision Transformers (ViTs) like DINO encode rich semantics, enabling training-free segmentation of objects from the background and discovery of their parts via feature clustering.Lifelong Context Adaptation through Bidirectional Memory-Skill Learning
Lifelong LLM agents must learn from an expanding history of interactions while making each decision within a bounded context window.DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks
Multi-stage analytical tasks require LLM agents to use intermediate evidence to decide whether to continue, redirect or stop.Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis
Multi-step retrosynthesis requires recursively transforming a target molecule through successive reaction steps into purchasable building blocks, and recent work has begun to draw on large language…Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement
LLM agents retrieve skills from public hubs that hold up to about 100,000 entries and serve many models.From Visual Affinity to Learning Credit in Multimodal Reinforcement Learning
Reinforcement learning with verifiable rewards (RLVR) improves multimodal reasoning, but uniformly assigning a single response-level advantage to all tokens overlooks the distinct roles of visual…ChoreoStudio: Planning What, When, and Who in Music-Driven Group Choreography
Music-driven group dance generation must decide not only how each dancer moves, but also what formation the group should form, when it should change, and who should execute each transition.TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent
Large Language Model (LLM) agents have enabled automated code evolution for algorithm discovery.4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents
Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicting long-horizon events.Data-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring
Pre-trained code models are exposed to backdoor poisoning, in which crafted training samples make the model misbehave on a trigger.TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection
In unsupervised multivariate time series anomaly detection (MTSAD), local variation can inflate reconstruction and forecasting errors, making observation-space discrepancy an unreliable indicator of…FOCUS: A Lightweight Mamba-2 Model for EEG-Based Cognitive Workload Classification
Cognitive workload estimation from physiological signals is increasingly relevant in high-risk environments, where continuous and unobtrusive monitoring can inform adaptive systems and safety…Adaptive Control of Scientific Instruments with Nonstationary Responses through Multimodal Agents
Controlling scientific instruments requires parameters to be adjusted progressively in response to feedback from successive operations.