An arXiv paper submitted on 23 Sep 2026 found that participants who read a misleading AI-generated summary of a car-pedestrian accident video accurately recalled the original event only 44.8 percent o…
A paper submitted to arXiv on 24 Sep 2026 introduces Codetta, a high-capacity steganographic protocol that lets independently deployed LLM agents collude undetectably in asymmetric settings without a …
Researchers introduced PFArena, a benchmark with four controlled task interfaces covering single-mutant generation and multi-mutant ranking, to compare protein language models (PLMs), large language m…
A new arXiv paper (2609.27150v1) reports that a simple random-without-replacement routing policy, in which each agent debates with two distinct newly sampled peers per round, consistently improves the…
A new paper titled "EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption" presents a GPU-accelerated implementation of fully homomorphic enc…
Researchers developed three methods that use large language models to incorporate rich auxiliary information into Bayesian Optimization, according to arXiv paper 2609.19437v1. The methods consistently…
A new arXiv paper (2609.19366v1) reports that category-specific harm representations in large language models carry safety-relevant information beyond a shared general harmfulness direction. Using act…
AI-powered search and answer engines are increasingly interpreting public reputation signals — reviews, ratings, listings, and location data — to generate recommendations, turning reputation managemen…
A new arXiv paper (2609.16779v1) presents the first end-to-end approach that enables large language models to perform the complete Analytic Hierarchy Process (AHP) workflow, according to its authors. …
Researchers proposed ReImaGin, a method that uses image generation models as a flexible visual reasoning mechanism for multimodal large language models, according to a new arXiv paper (2609.16409v1). …
Researchers proposed CLEAR, an agentic framework for cross-source evidence adjudication in large language models in medicine, detailed in arXiv paper 2609.16301v1. CLEAR independently generates candid…
Researchers introduced OrchSLM, a routing framework that unifies existing non-interactive small language model (SLM) orchestration methods and exposes their design choices as controllable parameters, …
A new arXiv paper (2609.13995v1) argues that the debate over synthetic data in marketing research should shift from whether LLM-generated respondents work to when they work, distinguishing three types…
Database administrators should treat AI as a process-following diagnostic assistant rather than a replacement, according to an InfoWorld opinion piece marking PostgreSQL's 30th anniversary. The author…
Generative AI, AI agents, and agentic AI are three distinct concepts that are commonly conflated, according to an analysis that defines GenAI as response-oriented content generation, AI agents as syst…
Traditional machine learning models are limited to static input-output mappings and cannot handle multi-step, dynamic, or action-requiring problems, according to an article explaining how combining tr…
A new arXiv paper (arXiv:2609.05459v1) proposes a deterministic framework that compiles games specified in the Video Game Description Language (VGDL) into Dynamic Structural Causal Models, directly tr…
A paper posted to arXiv (2609.05894v1) argues that the traditional scaling paradigms behind modern AI systems are hitting friction that prevents continued exponential growth, citing peak data limitati…
Researchers introduced Φ-Bench, a new benchmark designed to test whether large language models can engineer the infrastructure that powers them, according to the paper's headline and abstract. The wor…
Research on post-training large language models has largely overlooked whether complete reasoning traces—long trajectories that include detours toward an answer—are actually necessary, according to a …