Semantic Navigation for Issue Localization in Code Repository

arXiv:2609.31176 · cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Project page: https://microsoft.github.io/pyright

Terminology

• Benchmark — 8× in this paper · explained in 2 episodes
• Semantic Navigation Graph — 6× in this paper
• Core — 5× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Context Efficiency — 3× in this paper
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• First Useful Hit — 1× in this paper
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes

Sources

• REPOFUSE: Repository-Level Code Completion with Fused Dual Context
• Tool-integrated Reinforcement Learning for Repo Deep Search
• SweRank: Software Issue Localization with Code Ranking
• CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
• Extracting Conceptual Knowledge to Locate Software Issues
• OrcaLoca: An LLM Agent Framework for Software Issue Localization
• SWE-Explore: Benchmarking How Coding Agents Explore Repositories
• One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
• A Benchmark for Localizing Code and Non-Code Issues in Software Projects

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection