This paper introduces FINTAGGING, the first comprehensive benchmark for evaluating large language models on XBRL tagging tasks, decomposing the complex process into financial numeric identification and concept linking …
This paper presents OOPS (OpenAI OpenAPI Project Scanner), a novel LLM-based approach for automatically generating OpenAPI specifications from REST API source code across multiple programming languages and frameworks. …
LLMDFA introduces a novel framework that leverages Large Language Models to perform dataflow analysis on code without requiring compilation, achieving 87.10% precision and 80.77% recall for bug detection. The approach …
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 …
A new BCG experiment reveals that GenAI enables workers to perform complex tasks beyond their current skillset, such as data science work, even without prior coding experience. The study shows GenAI acts as an …
After analyzing over 50 agentic AI implementations, this article reveals six critical lessons for successfully deploying AI agents in enterprise workflows. The key insight is that success comes from reimagining entire …
Learn how Airbnb reduced a massive React testing library migration from 18 months to 6 weeks using AI-powered automation. This talk covers four foundational techniques for leveraging AI in code migrations, including …
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 …
This comprehensive research paper introduces Generative Engine Optimization (GEO) as a new paradigm for optimizing content visibility in AI-powered search engines like ChatGPT, Perplexity, and Gemini. The study reveals …
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, …
