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 126
Faithful Latent Harm Monitors Work No Better Than the Models Own Behaviour at a Matched False Alarm Rate
Large language models have been reported to encode the harmfulness of a request separately from their decision to refuse it, and latent safety monitors such as Latent Guard build on this report by…AgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes
When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting security events, and heterogeneous runtimes expose the relevant evidence through…How Firm Are AI Models' Ethical Boundaries? A Pay-Stub Editing Test of 15 Models
Can a small change in wording move an AI model from refusing a sensitive request to acting on it?The Delegation Divide: An Open Index of AI-Agent Delegability across Occupations and Countries
35.2% of task time in world employment is at least partly delegable to AI agents in 2026, and only 2.5% can be handed over in full.Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
LLM memory is widely used in long-term conversation understanding.Can Loan Processors and Underwriters Spot AI-Edited Statements? An Empirical Study
AI-assisted editing can produce loan documents that preserve familiar issuer layouts while changing the applicant's identity.AgentDP: Towards Automated Model Deployment for Heterogeneous Embedded AI Applications
This paper presents AgentDP, which aims to deploy pre-trained AI models on heterogeneous embedded devices by fully automating model optimization and adaptation (O&A) with Large Language Model (LLM)…Abstract Priorities, Concrete Rewards: How Stated Preferences Relate to What People Reward in AI Responses
AI assistants built on large language models (LLMs) are trained on human feedback and increasingly personalized to users' stated preferences.Scaling Laws for Generative Reward Models
We study generative reward models (GenRMs) as online preference providers for policy optimization in creative writing.LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades
Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by responding to others' choices, creating endogenous feedback loops with vulnerability to social…ProQuant: Preserving Expert Quality over Quantity in Ultra-Low-Bit Quantization of Mixture-of-Experts Models
Mixture-of-Experts (MoE) large language models reduce computation through sparse activation but still incur substantial storage costs.An Introduction to World Models for Generalist Agents
World models have recently emerged as a promising direction toward developing generalist agents capable of understanding, predicting, and interacting with diverse environments.Agentic Knowledge-Model Co-Evolution via Consistency Regularization
LLM agents can evolve by learning from accumulated experience.VLTest: Finding Joint Image-Text Failures in Vision-Language Models
Vision-language models (VLMs) are increasingly embedded in software systems.What Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight
Replacing the judge can move a benchmark score, and models can be trained to hide capabilities.TESSA: A Governance-Oriented Custom GPT for SME Guidance under the EU AI Act: Design, Implementation, and Evaluation
The increasing adoption of generative AI presents new opportunities while raising AI governance and regulatory challenges, particularly for small and medium-sized enterprises (SMEs) navigating the…Neural Spectral Capacity with Residual Context for Heterogeneous Resource Allocation within Transformers
Predicting relative trained performance from architectural specifications can guide design when training costs limit experimentation.One Evaluation Is Enough: Inversion-Free Image Editing with Trajectory Correction
Real-image editing commonly relies on inversion and iterative sampling, while efficient one-step editors often stabilize a large update by estimating and averaging editing fields at multiple noise…Semi-Linear Gaussian Bayesian Networks: Enhancing Flexibility in Node Dependencies via penalized B-Splines
Bayesian networks for continuous variables often rely on restrictive assumptions: linear Gaussian models lack flexibility to capture nonlinear dependencies, while non-parametric approaches provide…Bifurcations from Weight Space: JEPAWG on Parametric Dynamical Systems
Trained network weights are increasingly treated as data, but there is rarely ground truth about what a population of models should encode, which hampers systematic validation of weight-space methods.