Tagged articles

long-horizon

1 articles · Page 1 of 1
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jun 25, 2026 · Artificial Intelligence

Introducing DeNovoSWE: The First Long‑Horizon Doc2Repo Training Set for Code Agents

DeNovoSWE, a newly released large‑scale dataset of 4,818 high‑quality document‑to‑repository tasks, uses a Divide‑and‑Conquer and Critic‑Repair pipeline to generate well‑organized, evaluation‑aligned specifications, and experiments show it boosts LLM code agents’ repository‑level generation performance from single‑digit to over 40% on benchmarks.

LLMSoftware Engineeringbenchmark
0 likes · 10 min read
Introducing DeNovoSWE: The First Long‑Horizon Doc2Repo Training Set for Code Agents