🛰️ Daily AI Frontier
‹ back to 2026-08-17

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

Research LLM Agents

Ranking

Overall 79
Content 95
Popularity 41

Observed public metrics from 1 member.

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

Merged summary

TL;DR - Kozuchi is a language-agnostic, open-weight software-repair agent with an auditable CI evaluation pipeline. Using Qwen3.5-27B without fine-tuning, it achieves strong SWE-bench results across Python and Java.

  • Resolves 374/500 SWE-bench Verified tasks with test-time selection over eight candidates.
  • Solves 41/128 Multi-SWE-bench Java tasks, ranking first among strict open-weight submissions.
  • Uses explicit phases, persistent state, deterministic tools, and a model-independent action interface.
  • Analysis identifies semantic correctness and candidate selection—not patch formatting or proprietary-model access—as the main remaining limitations.

Sources (1)

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

arXiv cs.SE Mehdi Bahrami, Kosaku Kimura, Satoshi Munakata, Satoshi Nakashima, Yu Ishikawa, Kosuke Maeda, Nao Soma, Kenichi Kobayashi, Keisuke Miyazaki, Keizo Kato, Shigeki Fukuta, Tatsuo Kumano, Nobutaka Imamura, Kevin Musgrave, Shahbaz Abdul Khader, Kwun Ho Ngan, Joe Townsend, Fayas Asharindavida, Matthieu Parizy, Akira Sakai, Yuma Ichikawa, Yang Zhao, Michiaki Takizawa, Taku Fukui, Hiroki Ohtsuji, Wei-Peng Chen, Hiromichi Kobashi 2026-08-16 arXiv:2608.15579 doi:10.1145/3832783.3834531
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-09 08:14:20.606014 UTC

TL;DR - Kozuchi is a language-agnostic, open-weight software-repair agent with an auditable CI evaluation pipeline. Using Qwen3.5-27B without fine-tuning, it achieves strong SWE-bench results across Python and Java.

  • Resolves 374/500 SWE-bench Verified tasks with test-time selection over eight candidates.
  • Solves 41/128 Multi-SWE-bench Java tasks, ranking first among strict open-weight submissions.
  • Uses explicit phases, persistent state, deterministic tools, and a model-independent action interface.
  • Analysis identifies semantic correctness and candidate selection—not patch formatting or proprietary-model access—as the main remaining limitations.
item →