arXiv:2609.03407v1 Announce Type: new Abstract: People increasingly turn to large language models (LLMs) for everyday advice, making ethically charged…
The sameness problem behind those unappetizing AI-generated menus
While restaurant owners might look to generative AI as a shortcut to sprucing up their menu, customers can viscerally sense that something is wrong with…
DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents
arXiv:2609.03423v1 Announce Type: new Abstract: Full-duplex voice agents must continuously decide when to listen, backchannel, interrupt, handle speech…
Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory
arXiv:2609.03340v1 Announce Type: new Abstract: Distributed LLM-agent teams can read the latest shared facts and still act on an obsolete plan. A planner…
Speculative Macro Commit for Faster Tool-Using Agents
arXiv:2609.03236v1 Announce Type: new Abstract: Tool-using LLM agents spend wall-clock time not only on model inference but also in serial…
Structure and Implementation of New Practical English Textbooks Driven by Artificial Intelligence
arXiv:2609.02981v1 Announce Type: new Abstract: Artificial intelligence is changing the form of applied English materials from fixed paper sequences to…
MasterControl Seventeen Every Time
arXiv:2609.03209v1 Announce Type: new Abstract: We study a governed approach to enterprise analytics: a language model interprets the question, while…
A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant
arXiv:2609.03402v1 Announce Type: new Abstract: Artificial intelligence (AI) teaching assistants powered by large language models (LLMs) offer scalable…
AI News Brief Hourly Summary 2026-09-04 06h : 16 posts
16 posts published in the last hour 03:32On the Expressive Power and Limitations of Multi-Layer SSMs 03:32Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model 03:32US Department of Justice backs fair use for AI…
On the Expressive Power and Limitations of Multi-Layer SSMs
arXiv:2604.14501v2 Announce Type: replace-cross Abstract: We study how depth, finite precision, state dimension, and chain-of-thought (CoT) affect the…
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
arXiv:2603.25184v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs)…
US Department of Justice backs fair use for AI training in landmark copyright case
In the class-action lawsuit involving The New York Times, the US Department of Justice argues that training AI models on copyrighted text qualifies as…
FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment
arXiv:2603.19539v2 Announce Type: replace-cross Abstract: We introduce an expert curated, real-world benchmark for evaluating document-grounded…
From code to diagrams: Agentic architecture documentation with Amazon Bedrock AgentCore
Learn how a global interdealer broker built an automated architecture documentation pipeline on Amazon Bedrock AgentCore that analyzes .NET code bases,…
Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent
arXiv:2604.08552v3 Announce Type: replace-cross Abstract: Descriptive scientific metadata in public repositories are often incomplete and inconsistent…
Meet Switchyard: A Rust Proxy and Library That Routes and Translates LLM Traffic Across OpenAI and Anthropic APIs
NVIDIA has released Switchyard, an Apache-2.0 Rust proxy and library for LLM traffic. It decodes requests into provider-neutral types, routes them with…
CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation
arXiv:2604.20845v2 Announce Type: replace-cross Abstract: Next Point-of-Interest (POI) recommendation ranks a user’s likely next location based on…
FlatLands: Generative Floormap Completion From a Single Egocentric View
arXiv:2603.16016v3 Announce Type: replace-cross Abstract: A single egocentric image typically captures only a small portion of the floor, yet a complete…