Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition
Asif Mohammed Samir, Mohammad Masudur Rahman
TL;DR
CogniGent tackles bug localization by introducing an agent-based workflow that combines dynamic cognitive debugging with causal reasoning to navigate inter-component dependencies. It deploys six specialized AI agents, the Click2Cause call-chain exploration, and scratchpad-based context management to formulate and test root-cause hypotheses, delivering a ranked set of buggy components at multiple granularity levels. Evaluated on 591 bug reports across 15 Java systems, CogniGent outperforms traditional IR and LLM baselines in MAP and MRR, demonstrating substantial gains and robust performance across bug types and multi-component bugs. The work highlights the value of causal reasoning, dependency analysis, and context control in automated bug localization and provides a replication package to facilitate future research.
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.