# Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition

arXiv: https://arxiv.org/abs/2601.12522 · HTML: https://mlsanity.com/paper/2601.12522/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 88 references that are in the map.
- First posted on arXiv 18 Jan 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [The Effect of Sampling Temperature on Problem Solving in Large Language Models](https://mlsanity.com/paper/2402.05201/) (2024)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [LocAgent: Graph-Guided LLM Agents for Code Localization](https://mlsanity.com/paper/2503.09089/) (2025)
- [CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases](https://mlsanity.com/paper/2408.03910/) (2024)
- [NeuPSL: Neural Probabilistic Soft Logic](https://mlsanity.com/paper/2205.14268/) (2022)
- [SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning](https://mlsanity.com/paper/2406.01006/) (2024)
- [Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation](https://mlsanity.com/paper/2310.08395/) (2023)
- [Fast Changeset-based Bug Localization with BERT](https://mlsanity.com/paper/2112.14169/) (2021)
- [LLMs can be easily Confused by Instructional Distractions](https://mlsanity.com/paper/2502.04362/) (2025)
- [RACK: Automatic API Recommendation using Crowdsourced Knowledge](https://mlsanity.com/paper/1807.02953/) (2018)
- [Improving IR-Based Bug Localization with Context-Aware Query Reformulation](https://mlsanity.com/paper/1808.00594/) (2018)
- [BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning](https://mlsanity.com/paper/2407.17631/) (2024)
- [The Forgotten Role of Search Queries in IR-based Bug Localization: An Empirical Study](https://mlsanity.com/paper/2108.05341/) (2021)
- [Improved IR-based Bug Localization with Intelligent Relevance Feedback](https://mlsanity.com/paper/2501.10542/) (2025)
- [A Systematic Review of Automated Query Reformulations in Source Code Search](https://mlsanity.com/paper/2108.09646/) (2021)
- [Improving IR-based Bug Localization with Semantics-Driven Query Reduction](https://mlsanity.com/paper/2510.04468/) (2025)

## Abstract (arXiv)

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.