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: 4,993 arXiv preprints and 7 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 20
Coarse Semantic Blocks for Efficient Training-Free Sparse Attention
We introduce a training-free sparse attention method that builds a prompt-specific key index to accelerate both prefill and decoding.Drift No More: Spectral Locking for Long-Horizon Open-Weight Multi-Agent AI
Long-horizon multi-agent systems suffer from three tightly coupled failures: task drift, role drift, and state staleness.Planning-Coding Separation in LLM-Based Code Generation: An Empirical Study
Planning has been identified as an important factor for improved code generation with Large Language Models (LLMs).ATC: Agent Trajectory Control for Role-Contract Enforcement in Black-Box Multi-Agent Systems
Multi-agent LLM systems assign different responsibilities to different agents: one plans, another retrieves evidence, another verifies, another executes.FP4Quant: Efficient 4-Bit Communication Compression for Model-Parallel LLM Training
The rapid scaling of large language models (LLMs) has made communication overhead a critical bottleneck in distributed model-parallel training.Anchor: Augmented Cross-Layer Recurrent State for Long-Context Retrieval in Test-Time Training
Parameter-efficient linearization turns a pretrained autoregressive Transformer into an efficient model by hybridizing sliding-window attention (SWA) with a constant-size recurrent memory.CORA: Teacher-Guided Causal O-RAN Adaptation for Jamming Detection
In mission-critical networks, a missed jamming event is costlier than a false alarm, so detectors should favor recall, operate causally, and work without labeled attack data.Patching the Protocol: A Taxonomy of Pre-Registration Repairs in LLM-Proposer Experiments
Pre-registration is increasingly proposed as a trust mechanism for machine-learning research involving LLM-generated content, but its canonical form assumes a frozen protocol can be executed…Beyond Fine-Tuning: Evaluating Prompt Engineering and Prompt Tuning for Roman Urdu Hate Speech Detection
Low Resource Languages (LRLs) pose significant challenges for hate speech detection because of a scarcity of readily available annotated data, language variation, non-standard spelling, and…Large Language Models for Forecasting of Electricity Price Spikes
Can market notices read by a large language model (LLM) improve short-horizon electricity price spike forecasts?CloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion
Finite element method (FEM) solvers are foundational to scientific and engineering simulation, yet their susceptibility to \emph{efficiency attacks} remains largely unexplored.Benchmarking Unsupervised Jamming Detection in 5G Open RAN
Radio Frequency (RF) jamming threatens fifth-generation (5G) networks.Embodied AI for Scientific Discovery: From Physical Action to Scientific Evidence
Scientific experiments are increasingly selected, executed and interpreted by learned systems that act through physical interfaces.Aligning Training and Rollout Policies for End-to-End FP4 RL on Mixture-of-Experts LLMs
In this work, we study end-to-end FP4 reinforcement learning (RL) post-training for Mixture-of-Experts (MoE) large language models.Understanding Backdoor Attacks in Scene Graph Generation via Global Context Pathway
Scene Graph Generation (SGG) produces structured scene representations, yet its training-time backdoor risk remains unexplored.Twice as Fast, Until It Isn't: Quantized Serving of Mid-Size Open LLMs
A team serving a 9B-20B open-weight language model on vLLM or SGLang must choose a quantization recipe, and needs two numbers: the speedup over BF16 and the accuracy given up.Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs
Pretrained Vision-Language-Action (VLA) policies provide a strong starting point for deployment, but adapting them to a target robot and environment still requires costly embodiment-specific…Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents
LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a transaction, a dependency, or a decision with…Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior
Fine-tuning data can include metadata that predicts the correct answer, such as a reward-model score or a quality label.Silent Instrument Errors Reorder Agent Leaderboards
On a public agent leaderboard, a general-purpose agent trails a scaffold built for an airline customer-service benchmark by 13 points on the tasks that touch its database, and a reader could…