cs.SENov 5, 2026

NINJA: A Navigator-Inspector Joint Architecture for Context-Efficient Issue Localization

Authors: Wenkai Fang, Shunyu Liu, Wei Luo, Zihao Wu, Yang Zhou, Tongya Zheng, Wotao Yin, Jialie Shen, 

Organizations: Zhejiang University · DAMO Academy, Alibaba Group · College of Computing and Data Science, Nanyang Technological University, Singapore · Hangzhou City University · 

Abstract

Recent advances in agent-based methods have demonstrated strong promise for issue localization, a critical prerequisite for software issue resolution. However, most existing agent-based methods rely on a single agent with a growing context, where long-context accumulation compresses the effective reasoning space. Meanwhile, the flat exploration structure hinders the balance between file-level breadth and function-level depth. To address these limitations, we propose NINJA, a hierarchical Navigator-Inspector Joint Architecture for context-efficient issue localization. NINJA decomposes repository exploration into global navigation and local inspection: the navigator maintains the global search state, performs file-level search, and dispatches selected entry files, while inspectors independently conduct function-level exploration around the assigned files in separate contexts. Through multi-round interactions, inspectors return suspicious locations as feedback, and the navigator updates the global state to decide whether to continue exploration or finalize localization. This hierarchical design balances file-level breadth with function-level depth, while independent inspector contexts prevent local exploration traces from accumulating in a single growing context. To further strengthen both global coordination and local exploration, we introduce a two-stage agentic fine-tuning strategy. Extensive experiments across multiple benchmarks and LLM backbones show that NINJA consistently outperforms competitive baselines. Notably, after fine-tuning, Qwen3-Coder-30B-A3B-Instruct surpasses the strong closed-source Claude-Haiku-4.5 model. Our code is available at https://github.com/wantbook-book/NINJA.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Semantic Navigation for Issue Localization in Code Repository

    Sep 25, 2026Yunxiang Wei, Zhenyu Lei, Jundong LiSoftware Engineering AgentsLLM Grounding

  2. Exploration Structure in LLM Agents for Multi-File Change Localization

    Jun 10, 2026Akeela Darryl Fattha, Kia Ying Chua, Lingxiao Jiang +1Software EngineeringSoftware Engineering Agents