3 papers
cs.SE2026
IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks
Spencer Mateega, Jeff Yang, Tiana Costello +3
IDE-Bench is a comprehensive framework for evaluating AI IDE agents on real-world software engineering tasks through an IDE-native tool interface. We present a Dockerized test harn…
cs.SE2026
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
cs.CL2025
SuperRAG: Beyond RAG with Layout-Aware Graph Modeling
Jeff Yang, Duy-Khanh Vu, Minh-Tien Nguyen +3
This paper introduces layout-aware graph modeling for multimodal RAG. Different from traditional RAG methods that mostly deal with flat text chunks, the proposed method takes into…