In a new essay, Terence Tao warns that AI could push mathematics into a crisis on par with the foundational upheaval around 1900. What’s being tested this…
ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery
arXiv:2608.18846v1 Announce Type: new Abstract: Last-mile delivery aims to handle dynamically arriving orders with couriers while modeling complex spatial…
Guideless Raises €1M Pre-Seed to Turn Software Workflows Into AI Training Guides
Lithuanian AI startup Guideless has raised €1 million in pre-seed funding as it looks to rethink one of the less glamorous but persistent problems inside…
Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models
arXiv:2608.18884v1 Announce Type: new Abstract: Reinforcement-learning training of reasoning LLMs (e.g., GRPO) is expensive and requires a controllable…
How NVIDIA scales expertise with ChatGPT Work
NVIDIA teams use ChatGPT Work to reduce manual tasks, connect fast-moving signals, and scale successful workflows globally.
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
arXiv:2608.18852v1 Announce Type: new Abstract: Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on…
Auditing Preference Biases and Fine-Tuning Language Models with Direct Preference Optimization on Anthropic HH-RLHF Using TRL and LoRA
This tutorial provides an end-to-end workflow for fine-tuning language models using Direct Preference Optimization (DPO). We demonstrate how to audit the…
Verifiable abstention makes AI leak diagnosis accountable in water distribution networks
arXiv:2608.18836v1 Announce Type: new Abstract: Utilities lose a substantial share of treated water to leakage, yet rarely trust artificial-intelligence…
AI News Brief Hourly Summary 2026-08-20 11h : 17 posts
17 posts published in the last hour 08:32Pairwise Logical Selection of Enthymeme Completions under Semantic-Link Uncertainty 08:32A Multi-Agent Platform for Automated Enterprise Analytics and Insight Generation 08:32Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots 08:32A third…
Pairwise Logical Selection of Enthymeme Completions under Semantic-Link Uncertainty
arXiv:2608.18820v1 Announce Type: new Abstract: Arguments often omit premises or claims, forming enthymemes. We study pairwise logical selection between…
A Multi-Agent Platform for Automated Enterprise Analytics and Insight Generation
arXiv:2608.18740v1 Announce Type: new Abstract: This paper proposes a multi-agent framework built on CrewAI [1] for conversational business intelligence.…
Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
arXiv:2608.18744v1 Announce Type: new Abstract: Agents improve quickly against a reliable automatic metric and stall without one, and the applications…
A third of ChatGPT ads appear in irrelevant conversations
Advertising inside ChatGPT arrived with a promise that the assistant already knows what the user wants. So far, that hasn’t entirely been the case.…
Competence, Not Accuracy: A Diagnostic for Reference-Free Judge Gates in Skill Optimization
arXiv:2608.18719v1 Announce Type: new Abstract: Text-space skill optimization adapts a frozen agent by evolving a natural-language skill document,…
NVIDIA Releases TensorRT Model Connect in Public Preview: Hugging Face Checkpoint to Native C++ Inference in Two Commands
NVIDIA has released TensorRT Model Connect (TRTMC) in public preview, an Apache-2.0 project that takes a supported Hugging Face or local checkpoint to…
RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training
arXiv:2608.18682v1 Announce Type: new Abstract: Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to…
Sanyu Studio: A Multi-Agent System for Art-Historical Narrative Construction
arXiv:2608.18677v1 Announce Type: new Abstract: Amid concerns that generative AI may standardize art interpretation, this paper examines whether LLM-based…
OpenAI builds safety system that catches misuse without storing customer data
OpenAI plans to offer its most advanced AI models to corporate customers without storing their data, while still detecting misuse. The article OpenAI…