This paper presents a multi-agent AI architecture that achieves 92.1% reliability by organizing specialized AI agents into teams with opposing roles and hierarchical oversight, similar to corporate organizational …
GEPA introduces a novel prompt optimization approach that uses natural language reflection and Pareto-based evolutionary search to optimize compound AI systems, achieving superior performance compared to reinforcement …
A randomized controlled study examining how AI assistance affects skill formation in software development, finding that while AI can improve productivity, it significantly impairs conceptual understanding, code reading, …
Anthropic shares the engineering challenges and lessons learned from building Claude’s Research feature, a multi-agent system that uses multiple AI agents working in parallel to explore complex topics more …
This research proposes using distributed systems theory as a principled framework for designing and evaluating LLM teams, demonstrating that coordination challenges like consistency conflicts, communication overhead, and …
A comprehensive guide to using Gemini 2.5 Flash Image (Nano Banana) for generating consistent imagery from archive photos, demonstrating how to build a prompt-based pipeline that preserves character features across …
DRAGON-AI is a novel method that employs Large Language Models and Retrieval Augmented Generation to automatically generate ontology components including relationships, definitions, and logical axioms. The system …
This comprehensive review examines the bidirectional relationship between AI techniques and ontologies, exploring how machine learning contributes to automated ontology construction while ontologies enhance AI system …
A comprehensive exploration of how private data can be extracted from AI systems through various attack vectors including fine-tuned models, RAG systems, and vector embeddings. Demonstrates practical attacks against LLMs …
While frontier teams like StrongDM operate fully autonomous ‘dark factories’ where AI writes and ships code without human intervention, most developers using AI tools are actually getting 19% slower. This …
GenCAD introduces a novel AI framework that uses transformer-based contrastive learning and diffusion models to generate parametric CAD command sequences from image inputs, enabling the creation of editable 3D shapes for …
AutoResearch-RL presents a framework where reinforcement learning agents autonomously conduct neural architecture and hyperparameter research without human supervision, using PPO to optimize code modifications based on …
Anthropic announces that Claude Opus 4.6 and Sonnet 4.6 now support 1 million token context windows at standard pricing with no long-context premium, expanding media limits to 600 images or PDF pages.
