Sign inGet started
Paper · arXiv

Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair

Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long horizons, tool-use discipline, context persistence, heterogeneous clusters, and evaluation reuse. We present Kozuchi Agent, a language-agnostic open-weight repair agent and CI-operated evaluation pipeline. Explicit phases, persistent state, deterministic tools, a model-independent action interface, and cross-agent test-time selection make runs auditable and repeatable. With locally hosted Qwen3.5-27B, no fine-tuning, and TTS@8, Kozuchi resolves 374/500 SWE-bench Verified instances on the official evaluator. Unchanged on Multi-SWE-bench Java...

AuthorsMehdi Bahrami, Kosaku Kimura, Satoshi Munakata et al.
Primary categorycs.SE
Published16 August 2026
Last updated at source16 August 2026
cs.SEcs.AIcs.ETcs.PL
Embed this entry
<iframe src="https://silytics.si/embed/item/ffb02fe9-eac2-4b89-9e45-2c75047e14fb" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.