Software Engineering arXiv cs.AI

From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents

A 'harness-engineering' approach for enterprise LLM agents that moves deterministic behavior into code and schemas to ensure auditability and safety.

AI/ML arXiv cs.AI

Context Graphs for Proactive Enterprise Agents

Researchers propose the 'Context Graph', a live relational data structure and Delta Detection Engine to enable proactive enterprise AI agents that surface information before being queried.

AI/ML arXiv cs.AI

AI-integrated models for assessing agricultural resilience

A new AI-powered tool integrates economic (GTAP) and biophysical (APSIM) models to help policymakers assess agricultural supply chain resilience using natural language queries.

AI/ML arXiv cs.AI

Adversarial Social Epistemology for Assemblies of Humans and Large Language Models

This paper introduces Adversarial Social Epistemology (ASE) to analyze and audit trust breaches in complex communicative landscapes involving humans and LLMs.

AI/ML arXiv cs.AI

Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning

A survey on LLMs for medical reasoning that establishes a five-level competency scheme and a benchmark dataset to evaluate specialist vs general models.

AI/ML arXiv cs.AI

Alignment Plausibility: A New Standard for Assuring AI in Healthcare

The authors propose 'alignment plausibility' as a regulatory construct to ensure AI in healthcare is aligned with clinical safety norms and patient benefit.

AI/ML arXiv cs.AI

Idiobionics: The Unification of Privacy and Intelligent Robotic Prostheses

The paper introduces 'idiobionics', a field of inquiry focused on the privacy risks and adversarial attacks associated with intelligent robotic prostheses.

AI/ML arXiv cs.AI

Infinity-Parser2 Technical Report

Infinity-Parser2 is a multimodal model for document parsing that introduces the Infinity-Doc2-5M bilingual corpus and achieves SOTA performance in OCR and layout analysis.

AI/ML arXiv cs.AI

VectorizationLLM: Smart Vectorization Based AI Assistant

VectorizationLLM is a RAG-based assistant designed to help students learn vector analysis and differential equations in MATLAB.

AI/ML arXiv cs.AI

A Graph Neural Network Model for Real-Time Gesture Recognition Based on sEMG Signals

A novel Graph Neural Network (GNN) approach for real-time hand gesture recognition using sEMG signals achieves 99% accuracy with low latency on M1 CPUs.

AI/ML arXiv cs.AI

Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting

An analysis of agentic AI frameworks in insurance underwriting, demonstrating that multi-agent 'Agentic RAG' pipelines outperform single-LLM and naive RAG systems.

Tech Business/VC Hacker News

Ben Bernanke Joins Anthropic Oversight Trust

Ben Bernanke has joined the Anthropic Oversight Trust, focusing on governance and oversight of the AI company.

Hardware/Chips Hacker News

Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

An Apple Silicon executive discusses the high demand for Mac Mini AI capabilities and the future of on-device AI processing.

Open Source Phoronix

Razer Certifying Their First Laptop For Linux: Razer Blade 18 RZ09-0582

Razer is certifying its first laptop, the Razer Blade 18, for Ubuntu Linux, marking a significant move for gaming hardware vendors.

Hardware/Chips Phoronix

NVIDIA Confirms Some Rosa CPU Details With Its Rigel Core

NVIDIA confirms details about its next-generation Rosa CPU featuring the 'Rigel' core, focusing on single-threaded performance.

Open Source Phoronix

NVIDIA 610.43.03 Linux Driver Released With Unspecified Fixes

NVIDIA has released the 610.43.03 Linux driver update with various unspecified fixes.

Open Source Phoronix

TUXEDO Computers Switching TUXEDO OS From Ubuntu To Debian Testing

TUXEDO Computers is switching the base of TUXEDO OS from Ubuntu to Debian Testing, aiming for more current packages.

Cybersecurity Phoronix

AF_ALG "Nightmare" Being Further Limited In Linux 7.3 With New Sysctl Knob

The Linux kernel's AF_ALG interface is being further restricted in Linux 7.3 to reduce the attack surface for security concerns.

Software Engineering Phoronix

"I'll Make The Linux Kernel Mailing List Burn": Prominent LLVM Linux Developer Returns

A prominent developer returns to work on LLVM/Clang support for the Linux kernel, enhancing portability and Rust integration.

Open Source Phoronix

EHEA 10Gb Ethernet Driver Being Retired By IBM As A Relic Of Outdated POWER Hardware

IBM is retiring the EHEA 10Gb Ethernet driver from the Linux kernel as it targets outdated POWER hardware.