Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding
This addresses the debugging bottleneck for software developers, offering a substantial improvement over current models, though it is incremental in advancing debugging capabilities.
The paper tackles the problem of debugging code with large language models, which have low accuracy on real debugging tasks, and introduces Kodezi Chronos, a model that achieves 67.3% fix accuracy on real-world scenarios and 80.33% resolution rate on SWE-bench Lite, outperforming existing models by significant margins.
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 Sonnet and Claude 4.1 Opus exceed 70% on code synthesis benchmarks, they achieve under 15% on real debugging tasks. We introduce Kodezi Chronos, a language model purpose-built for debugging that integrates Adaptive Graph-Guided Retrieval to traverse codebases up to 10 million lines, Persistent Debug Memory trained on over 15 million sessions, and a seven-layer fix-test-refine architecture. On 5,000 real-world scenarios, Chronos achieves 67.3% fix accuracy compared to 14.2% and 13.8% for Claude 4.1 Opus and GPT-4.1, respectively. On SWE-bench Lite, Chronos 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 reduces debugging time by 40% and iterations by 65%, resolving complex multi-file and cross-repository bugs. It remains limited on hardware-dependent and dynamic language errors. Chronos will be available in Kodezi OS in Q4 2025 and via API in Q1 2026.