2025/07/14 by Khan, Ishraq, Chowdary, Assad, Haseeb, Sharoz +2 · 1 citation
#68N30 #68Q60 #68T05 #68T20 #68T30 #68T37 #68T50 #Artificial Intelligence (cs.AI) #Computational Engineering #D.2.3 #D.2.5 #D.2.7 #F.3.2 #FOS: Computer and information sciences #Finance #H.3.3 #I.2.2 #I.2.6 #I.2.7 #I.2.8 #Machine Learning (cs.LG) #Software Engineering (cs.SE) #and Science (cs.CE)
paper · doi:10.48550/arxiv.2507.12482
Large Language Models (LLMs) have advanced code generation and software automation but remain constrained by inference-time context and lack structured reasoning over code, leaving debugging largely unsolved. While Claude 4.5 Opus achieves 74.40% on SWE-bench Verified and Gemini 3 Pro reaches 76.2%, both models remain below 20% on real multi-file debugging tasks. We introduce Kodezi Chronos-1, a language model purpose-built for debugging that integrates Adaptive Graph-Guided Retrieval to navigate codebases up to 10 million lines (92% precision, 85% recall), Persistent Debug Memory trained on over 15 million sessions, and a seven-layer fix-test-refine architecture. On 5,000 real-world scenarios, Chronos-1 achieves 67.3% +/- 2.1% fix accuracy compared to 14.2% +/- 1.3% for Claude 4.1 Opus and 13.8% +/- 1.2% for GPT-4.1 (Cohen's d = 3.87). On SWE-bench Lite, Chronos-1 reaches a state-of-the-art 80.33% resolution rate (241 of 300), outperforming the next best system by 20 points and achieving repository-specific highs of 96.1% on Sympy and 90.4% on Django. Chronos-1 reduces debugging time by 40% and iterations by 65%, resolving complex multi-file and cross-repository bugs that require temporal analysis. Limitations remain for hardware-dependent and dynamic language errors, and Chronos-1 will be available in Kodezi OS in Q4 2025 and via API in Q1 2026.