Boosting LLMs for Mutation Generation

• URL: http://arxiv.org/abs/2603.24560v1
• Date: Wed, 25 Mar 2026 17:42:17 GMT
• Title: Boosting LLMs for Mutation Generation
• Abstract summary: We introduce SMART (Semantic Mutation with Adaptive Retrieval and Tuning)<n>We conduct an empirical study of SMART using 1,991 real-world Java bugs from Defects4J and ConDefects datasets.<n>The results reveal that SMART substantially improves mutation validity, effectiveness, and efficiency.
• Score: 35.905252475438466
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based mutation testing is a promising testing technology, but existing approaches typically rely on a fixed set of mutations as few-shot examples or none at all. This can result in generic low-quality mutations, missed context-specific mutation patterns, substantial numbers of redundant and uncompilable mutants, and limited semantic similarity to real bugs. To overcome these limitations, we introduce SMART (Semantic Mutation with Adaptive Retrieval and Tuning). SMART integrates retrieval-augmented generation (RAG) on a vectorized dataset of real-world bugs, focused code chunking, and supervised fine-tuning using mutations coupled with real-world bugs. We conducted an extensive empirical study of SMART using 1,991 real-world Java bugs from the Defects4J and ConDefects datasets, comparing SMART to the state-of-the-art LLM-based approaches, LLMut and LLMorpheus. The results reveal that SMART substantially improves mutation validity, effectiveness, and efficiency (even enabling small-scale 7B-scale models to match or even surpass large models like GPT-4o). We also demonstrate that SMART significantly improves downstream software engineering applications, including test case prioritization and fault localization. More specifically, SMART improves validity (weighted average generation rate) from 42.89% to 65.6%. It raises the non-duplicate rate from 87.38% to 95.62%, and the compilable rate from 88.85% to 90.21%. In terms of effectiveness, it achieves a real bug detection rate of 92.61% (vs. 57.86% for LLMut) and improves the average Ochiai coefficient from 25.61% to 38.44%. For fault localization, SMART ranks 64 more bugs as Top-1 under MUSE and 57 more under Metallaxis.

Related papers

• Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions [52.50730821321986]
  We present the first large-scale measurement study of version-level risk in large language models (LLMs)<n>We evaluate 10 LLMs on PinTrace, a curated benchmark of 1,000 Stack Overflow programming tasks.<n>Our findings reveal LLM version selection as a first-class, previously overlooked risk surface in LLM-based development.
  arXiv  Detail & Related papers  (2026-05-07T13:52:59Z)
• Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis [68.28714988482703]
  Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs)<n>We present a study revealing that general-domain PRMs struggle to supervise data analysis agents.<n>We introduce DataPRM, a novel environment-aware generative process reward model.
  arXiv  Detail & Related papers  (2026-04-27T09:00:30Z)
• Examining LLMs Ability to Summarize Code Through Mutation-Analysis [9.187740569361804]
  We present a mutation-based evaluation methodology that directly tests whether a summary truly matches the code's logic.<n>We validate it through three experiments totalling 624 mutation-summary evaluations across 62 programs.<n>We find that summary accuracy decreases sharply with complexity, while mutation type and location exhibit weaker effects.
  arXiv  Detail & Related papers  (2026-02-19T21:00:49Z)
• 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)
• Extended LSTM: Adaptive Feature Gating for Toxic Comment Classification [0.0]
  xLSTM is a framework that unifies cosine-similarity gating, adaptive feature prioritization, and principled class rebalancing.<n>On the Jigsaw Toxic Comment benchmark, xLSTM attains 96.4% accuracy and 0.88 macro-F1, outperforming BERT by 33% on threat and 28% on identity_hate categories.
  arXiv  Detail & Related papers  (2025-10-19T21:50:04Z)
• LLAMA: Multi-Feedback Smart Contract Fuzzing Framework with LLM-Guided Seed Generation [56.84049855266145]
  We propose a Multi-feedback Smart Contract Fuzzing framework (LLAMA) that integrates evolutionary mutation strategies, and hybrid testing techniques.<n>LLAMA achieves 91% instruction coverage and 90% branch coverage, while detecting 132 out of 148 known vulnerabilities.<n>These results highlight LLAMA's effectiveness, adaptability, and practicality in real-world smart contract security testing scenarios.
  arXiv  Detail & Related papers  (2025-07-16T09:46:58Z)
• BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis [1.9291502706655312]
  We introduce BugGen, a first of its kind, fully autonomous, multi-agent pipeline to generate, insert, and validate functional bugs in RTL.<n> BugGen partitions modules, selects mutation targets via a closed-loop agentic architecture, and employs iterative refinement and rollback mechanisms.<n> evaluated across five OpenTitan IP blocks, BugGen produced 500 unique bugs with 94% functional accuracy and achieved a throughput of 17.7 validated bugs per hour-over five times faster than typical manual expert insertion.
  arXiv  Detail & Related papers  (2025-06-12T09:02:20Z)
• Early Diagnosis of Alzheimer's Diseases and Dementia from MRI Images Using an Ensemble Deep Learning [0.7510165488300369]
  Alzheimer's Disease (AD) is a progressive neurological disorder that can result in significant cognitive impairment and dementia.<n>In this study, we proposed two CNNs, IR-BRAINNET and Modified-DEMNET, designed to detect the early stages of AD accurately.<n>We also introduced an ensemble model that averages their outputs to reduce variance across the CNNs and enhance AD detection.
  arXiv  Detail & Related papers  (2024-12-07T14:27:41Z)
• A Comprehensive Study on Large Language Models for Mutation Testing [36.00296047226433]
  Large Language Models (LLMs) have recently been used to generate mutants in both research work and in industrial practice.<n>We evaluate BugFarm and LLMorpheus (the two state-of-the-art LLM-based approaches) on 851 real bugs from two Java real-world bug benchmarks.<n>Our results reveal that, compared to existing rule-based approaches, LLMs generate more diverse mutants, that are behaviorally closer to real bugs and, most importantly, with 111.29% higher fault detection.
  arXiv  Detail & Related papers  (2024-06-14T08:49:41Z)
• Less is More: Fewer Interpretable Region via Submodular Subset Selection [54.07758302264416]
  This paper re-models the above image attribution problem as a submodular subset selection problem. We construct a novel submodular function to discover more accurate small interpretation regions. For correctly predicted samples, the proposed method improves the Deletion and Insertion scores with an average of 4.9% and 2.5% gain relative to HSIC-Attribution.
  arXiv  Detail & Related papers  (2024-02-14T13:30:02Z)

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.