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 185
Multiple Turns, Short Horizons: Measuring Effective-Horizon Compression in Jailbreaks
Multi-turn jailbreaks use feedback from a victim large language model to adapt their queries over several turns.Many Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism
Language models often abandon a correct answer when the prompt contains a cue, a hint toward a wrong option such as "I think the answer is B." Sycophancy and related biases show this failure.Aligning Language Models Towards Counterfactual Invariance
Small variations in prompt characteristics can meaningfully alter the semantics, tone, and contextual assumptions of large language model outputs.NL2SQL with Iterative Self-Refinement
Bridging the gap between human intent and machine logic remains a critical challenge in data access for non-technical users, yet Large Language Models (LLMs) remain unreliable: they hallucinate…DiffusionRVGE: Reinforcement Learning via Regression-Based Value Gradient Estimation
Reinforcement learning improves diffusion models using rewards on generated images, but repeated denoising and gradient estimation make training expensive.Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
Long-context decoding in large language models (LLMs) is increasingly bottlenecked by the memory and computation required to attend over an ever-growing Key-Value (KV) cache at each autoregressive…From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents
Coding agents use execution harnesses to constrain the consequences of prompt injection by enforcing permission boundaries.PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas
Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions.GOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding
Designing RNA sequences that fold into specific 3D structures is a fundamental challenge in therapeutics.A Label Noise Robust Algorithm for Graph Data using Neighborhood Label Distribution
Graph Convolutional Networks (GCNs) have demonstrated exceptional performance on graph-structured data.Efficient CPU-GPU collaborative MoE inference via Adaptive Expert Assignment
Mixture-of-Experts (MoE) models reduce inference computation through sparse expert activation, but their large expert memory footprint often exceeds GPU capacity, making expert offloading necessary…Adaptation of Computer Use Agents to New Software with User Manuals
Recent advances in multimodal foundation models have significantly improved the ability to operate real-world software through graphical user interfaces (GUIs) using visual observations and natural…Causal Value Attribution of Marketing Labels in LLM-Generated Ads: A Deconfounder Approach
As AI-generated content becomes commoditized, economic value increasingly shifts from final artifacts to the upstream expertise used to specify inputs that steer LLM generation.ASE: Attribution-Guided Semantic Evolution for Time Series Forecasting
External text can supply predictive information absent from numerical histories, but its value depends on how it is represented, combined and deployed.Where Research Ideation Begins: Forward-Citation Supervision for Actionable Limitation Generation
Automated research ideation has advanced rapidly, with multi-agent workflows that generate whole research ideas end to end.Where Does the Performance Go? Understanding and Recovering Performance Regressions in C-to-Rust Translation
Rust is increasingly adopted as a memory-safe successor to C, and transpilers such as \crust{} can migrate entire C projects while preserving their behavior.SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks
On neuromorphic chips, spiking neural networks (SNNs) consume far less energy than artificial neural networks (ANNs), but the limited memory of these chips requires low-bit synaptic weights and…Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL
Long-horizon interaction requires agents to make multiple decisions in a changing environment.Agentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?
The learning algorithm view of in-context learning (ICL) studies how fixed-parameter Transformers learn from supplied examples.Unifying Embodied Foundation Models via a Model-to-Policy Formulation
Vision-language-action (VLA) models and world-action models (WAMs) have emerged as promising approaches to robot learning and control.