Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911298508292096 |
|---|---|
| author | Khan, Ishraq Chowdary, Assad Haseeb, Sharoz Patel, Urvish Zaii, Yousuf |
| author_facet | Khan, Ishraq Chowdary, Assad Haseeb, Sharoz Patel, Urvish Zaii, Yousuf |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12482 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding Khan, Ishraq Chowdary, Assad Haseeb, Sharoz Patel, Urvish Zaii, Yousuf Software Engineering Artificial Intelligence Computational Engineering, Finance, and Science Machine Learning 68N30, 68Q60, 68T05, 68T20, 68T30, 68T37, 68T50 D.2.3; D.2.5; D.2.7; F.3.2; H.3.3; I.2.2; I.2.6; I.2.7; I.2.8 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. |
| title | Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding |
| topic | Software Engineering Artificial Intelligence Computational Engineering, Finance, and Science Machine Learning 68N30, 68Q60, 68T05, 68T20, 68T30, 68T37, 68T50 D.2.3; D.2.5; D.2.7; F.3.2; H.3.3; I.2.2; I.2.6; I.2.7; I.2.8 |
| url | https://arxiv.org/abs/2507.12482 |