Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition

2026-01-18

AI Summary

This work proposes CogniGent, a novel multi-agent framework for software defect localization that addresses key limitations of existing approaches—either analyzing code components in isolation while neglecting dependencies or being constrained by large language models’ (LLMs) limited causal reasoning and inefficient context management. CogniGent uniquely integrates causal reasoning, call graph-based root cause analysis, and a dynamic cognitive debugging mechanism, leveraging hypothesis-driven inference and context engineering to jointly model code dependencies and debugging logic. Evaluated on 591 real-world defects, CogniGent significantly outperforms six state-of-the-art baselines, achieving relative improvements of 23.33–38.57% in Mean Average Precision (MAP) and 25.14–53.74% in Mean Reciprocal Rank (MRR), with statistical significance (p < 0.01), thereby demonstrating its effectiveness and innovation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Software bugs cost technology providers (e.g., AT&T) billions annually and cause developers to spend roughly 50% of their time on bug resolution. Traditional methods for bug localization often analyze the suspiciousness of code components (e.g., methods, documents) in isolation, overlooking their connections with other components in the codebase. Recent advances in Large Language Models (LLMs) and agentic AI techniques have shown strong potential for code understanding, but still lack causal reasoning during code exploration and struggle to manage growing context effectively, limiting their capability. In this paper, we present a novel agentic technique for bug localization -- CogniGent -- that overcomes the limitations above by leveraging multiple AI agents capable of causal reasoning, call-graph-based root cause analysis and context engineering. It emulates developers-inspired debugging practices (a.k.a., dynamic cognitive debugging) and conducts hypothesis testing to support bug localization. We evaluate CogniGent on a curated dataset of 591 bug reports using three widely adopted performance metrics and compare it against six established baselines from the literature. Experimental results show that our technique consistently outperformed existing traditional and LLM-based techniques, achieving MAP improvements of 23.33-38.57% at the document and method levels. Similar gains were observed in MRR, with increases of 25.14-53.74% at both granularity levels. Statistical significance tests also confirm the superiority of our technique. By addressing the reasoning, dependency, and context limitations, CogniGent advances the state of bug localization, bridging human-like cognition with agentic automation for improved performance.

Problem

• bug localization
• causal reasoning
• code dependencies
• context management
• AI agents

Innovation

• agentic AI
• causal reasoning
• call-graph analysis
• dynamic cognitive debugging
• context engineering