Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition

• URL: http://arxiv.org/abs/2601.12522v1
• Date: Sun, 18 Jan 2026 18:12:21 GMT
• Title: Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition
• Authors: Asif Mohammed Samir, Mohammad Masudur Rahman,
• Abstract summary: Software bugs cost technology providers (e.g., AT&T) billions annually and cause developers to spend roughly 50% of their time on bug resolution.<n>Traditional methods for bug localization often analyze the suspiciousness of code components in isolation.<n>Recent advances in Large Language Models (LLMs) and agentic AI techniques have shown strong potential code understanding, but still lack causal reasoning during code exploration.<n>We present a novel agentic technique for bug localization -- CogniGent -- that overcomes the limitations above by multiple AI agents capable of causal reasoning, call-graph-based root cause analysis and context.
• Score: 0.9298382208776371
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Cognitive Foundations for Reasoning and Their Manifestation in LLMs [63.12951576410617]
  Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning.<n>We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning reasoning invariants, meta-cognitive controls, representations for organizing reasoning & knowledge, and transformation operations.<n>We develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 66.7% on complex problems.
  arXiv  Detail & Related papers  (2025-11-20T18:59:00Z)
• BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills [59.003563837981886]
  High quality bugs are key to training the next generation of language model based software engineering (SWE) agents.<n>We introduce a novel method for synthetic generation of difficult and diverse bugs.
  arXiv  Detail & Related papers  (2025-10-22T17:58:56Z)
• Executable Knowledge Graphs for Replicating AI Research [65.41207324831583]
  Executable Knowledge Graphs (xKG) is a modular and pluggable knowledge base that automatically integrates technical insights, code snippets, and domain-specific knowledge extracted from scientific literature.<n>Code will released at https://github.com/zjunlp/xKG.
  arXiv  Detail & Related papers  (2025-10-20T17:53:23Z)
• Improving IR-based Bug Localization with Semantics-Driven Query Reduction [0.9298382208776371]
  We propose IQLoc, a novel approach to localize software bugs against bug reports.<n>We leverage the program semantics understanding of transformer-based models to reason about the suspiciousness of code.<n> IQLoc improves MAP by 91.67% for bug reports with stack traces, 72.73% for those that include code elements, and 65.38% for those containing only descriptions in natural language.
  arXiv  Detail & Related papers  (2025-10-06T03:43:38Z)
• CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection [60.52240468810558]
  We introduce CoCoNUTS, a content-oriented benchmark built upon a fine-grained dataset of AI-generated peer reviews.<n>We also develop CoCoDet, an AI review detector via a multi-task learning framework, to achieve more accurate and robust detection of AI involvement in review content.
  arXiv  Detail & Related papers  (2025-08-28T06:03:11Z)
• Towards Understanding Bugs in Distributed Training and Inference Frameworks for Large Language Models [7.486731499255164]
  This paper conducts the first large-scale empirical analysis of 308 fixed bugs across three popular distributed training/inference frameworks: DeepSpeed, Megatron-LM, and Colossal-AI.<n>We examine bug symptoms, root causes, bug identification and fixing efforts, and common low-effort fixing strategies.
  arXiv  Detail & Related papers  (2025-06-12T07:24:59Z)
• Improved IR-based Bug Localization with Intelligent Relevance Feedback [2.9312156642007294]
  Software bugs pose a significant challenge during development and maintenance, and practitioners spend nearly 50% of their time dealing with bugs.<n>Many existing techniques adopt Information Retrieval (IR) to localize a reported bug using textual and semantic relevance between bug reports and source code.<n>We present a novel technique for bug localization - BRaIn - that addresses the contextual gaps by assessing the relevance between bug reports and code.
  arXiv  Detail & Related papers  (2025-01-17T20:29:38Z)
• Continuously Learning Bug Locations [11.185300073739098]
  We evaluate the potential of using Continual Learning (CL) techniques in multiple sub-tasks setting for bug localization.<n>We show that CL techniques perform better than DL-based techniques by up to 61% in terms of Mean Reciprocal Rank (MRR), 44% in terms of Mean Average Precision (MAP), 83% in terms of top@1, 56% in terms of top@5, and 66% in terms of top@10 metrics in non-stationary setting.
  arXiv  Detail & Related papers  (2024-12-15T19:37:15Z)
• Boosting CNN-based Handwriting Recognition Systems with Learnable Relaxation Labeling [48.78361527873024]
  We propose a novel approach to handwriting recognition that integrates the strengths of two distinct methodologies. We introduce a sparsification technique that accelerates the convergence of the algorithm and enhances the overall system's performance.
  arXiv  Detail & Related papers  (2024-09-09T15:12:28Z)
• A Comparative Study of Transformer-based Neural Text Representation Techniques on Bug Triaging [8.831760500324318]
  We offer one of the first investigations that fine-tunes transformer-based language models for the task of bug triaging. DeBERTa is the most effective technique across the triaging tasks of developer and component assignment.
  arXiv  Detail & Related papers  (2023-10-10T18:09:32Z)
• BigIssue: A Realistic Bug Localization Benchmark [89.8240118116093]
  BigIssue is a benchmark for realistic bug localization. We provide a general benchmark with a diversity of real and synthetic Java bugs. We hope to advance the state of the art in bug localization, in turn improving APR performance and increasing its applicability to the modern development cycle.
  arXiv  Detail & Related papers  (2022-07-21T20:17:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.