TriagerX: Dual Transformers for Bug Triaging Tasks with Content and Interaction Based Rankings

2025-08-22

AI Summary

Existing PLM-based bug assignment methods are susceptible to noise from irrelevant textual content and overlook historical developer interactions around similar bugs, leading to biased recommendations. To address these limitations, we propose a dual-Transformer fusion framework that jointly models issue report semantics and cross-bug developer collaboration patterns. Specifically, two parallel Transformer encoders independently process the bug report text and the historical interaction graph, enabling multi-granularity semantic alignment; a joint ranking mechanism then unifies optimization for both component and developer recommendation. Evaluated on five benchmark datasets, our approach consistently outperforms nine state-of-the-art methods, achieving average improvements of over 10% in Top-1 and Top-3 accuracy. In industrial deployment, it yields a 10% gain in component recommendation accuracy and a remarkable 54% improvement in developer recommendation accuracy—demonstrating the effectiveness and practicality of dual-dimensional (content + interaction) modeling.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Pretrained Language Models or PLMs are transformer-based architectures that can be used in bug triaging tasks. PLMs can better capture token semantics than traditional Machine Learning (ML) models that rely on statistical features (e.g., TF-IDF, bag of words). However, PLMs may still attend to less relevant tokens in a bug report, which can impact their effectiveness. In addition, the model can be sub-optimal with its recommendations when the interaction history of developers around similar bugs is not taken into account. We designed TriagerX to address these limitations. First, to assess token semantics more reliably, we leverage a dual-transformer architecture. Unlike current state-of-the-art (SOTA) baselines that employ a single transformer architecture, TriagerX collects recommendations from two transformers with each offering recommendations via its last three layers. This setup generates a robust content-based ranking of candidate developers. TriagerX then refines this ranking by employing a novel interaction-based ranking methodology, which considers developers' historical interactions with similar fixed bugs. Across five datasets, TriagerX surpasses all nine transformer-based methods, including SOTA baselines, often improving Top-1 and Top-3 developer recommendation accuracy by over 10%. We worked with our large industry partner to successfully deploy TriagerX in their development environment. The partner required both developer and component recommendations, with components acting as proxies for team assignments-particularly useful in cases of developer turnover or team changes. We trained TriagerX on the partner's dataset for both tasks, and it outperformed SOTA baselines by up to 10% for component recommendations and 54% for developer recommendations.

Problem

• Improves bug report token relevance in developer recommendation systems
• Incorporates developer interaction history with similar fixed bugs
• Enhances accuracy for both developer and component assignment tasks

Innovation

• Dual-transformer architecture for robust content ranking
• Interaction-based ranking using developer historical data
• Outperforms SOTA baselines in developer recommendation accuracy