Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap
2025/05/26 by Hassan Sartaj, Shaukat Ali, Sartaj, Hassan +5 · 1 citation
Decision Sciences · #Scientific Computing and Data Management
paper · pdf · doi:10.48550/arxiv.2505.19625
Abstract
Search-based software engineering (SBSE), which integrates metaheuristic search techniques with software engineering, has been an active area of research for about 25 years. It has been applied to solve numerous problems across the entire software engineering lifecycle and has demonstrated its versatility in multiple domains. With recent advances in Artificial Intelligence (AI), particularly the emergence of foundation models (FMs) such as large language models (LLMs), the evolution of SBSE alongside these models remains undetermined. In this window of opportunity, we present a research roadmap that articulates the current landscape of SBSE in relation to FMs, identifies open challenges, and outlines potential research directions to advance SBSE through its synergy with FMs. Specifically, we analyze three core aspects: utilizing FMs to enhance SBSE, applying SBSE to advance FMs, and exploring the integration of SBSE and FMs. Furthermore, we present a forward-thinking perspective that envisions the future of SBSE in the era of FMs, highlighting promising research opportunities to address challenges in emerging domains.
Citations
- Generative AI for Testing of Autonomous Driving Systems: A Survey
- FairFLRep: Fairness aware fault localization and repair of Deep Neural Networks
- Vision Language Action Models in Robotic Manipulation: A Systematic Review
- Prompting for Performance: Exploring LLMs for Configuring Software
- Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
- Quantum-Based Software Engineering
- Quantum Artificial Intelligence for Software Engineering: the Road Ahead
- Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges
- Identifying Uncertainty in Self-Adaptive Robotics with Large Language Models
- RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search
- A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook
- KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
- ProAPO: Progressively Automatic Prompt Optimization for Visual Classification
- A Survey of Automatic Prompt Engineering: An Optimization Perspective
- Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization
- An Analysis of LLM Fine-Tuning and Few-Shot Learning for Flaky Test Detection and Classification
- Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation
- LlamaRestTest: Effective REST API Testing with Small Language Models
- Improving the Readability of Automatically Generated Tests using Large Language Models
- Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection
- REST API Testing in DevOps: A Study on an Evolving Healthcare IoT Application
- Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models
- VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model
- An Adaptive Re-evaluation Method for Evolution Strategy under Additive Noise
- LeGEND: A Top-Down Approach to Scenario Generation of Autonomous Driving Systems Assisted by Large Language Models
- Search-Based LLMs for Code Optimization
- Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm
- GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation
- Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software
- Search-based DNN Testing and Retraining with GAN-enhanced Simulations
- A Survey on Large Language Models for Code Generation
- IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
- Enhancing Decision-Making in Optimization through LLM-Assisted Inference: A Neural Networks Perspective
- Large Language Model-Aided Evolutionary Search for Constrained Multiobjective Optimization
- LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
- Rethinking Software Engineering in the Foundation Model Era: From Task-Driven AI Copilots to Goal-Driven AI Pair Programmers
- A Generic Approach to Fix Test Flakiness in Real-World Projects
- Improving Text-to-Image Consistency via Automatic Prompt Optimization
- Reality Bites: Assessing the Realism of Driving Scenarios with Large Language Models
- Search-Based Optimisation of LLM Learning Shots for Story Point Estimation
- Explaining Genetic Programming Trees using Large Language Models
- A Disruptive Research Playbook for Studying Disruptive Innovations
- SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization
- LLMs in the Heart of Differential Testing: A Case Study on a Medical Rule Engine
- ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
- Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap
- TestSpark: IntelliJ IDEA's Ultimate Test Generation Companion
- Large Language Models for Robotics: Opportunities, Challenges, and Perspectives
- Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
- A Survey on Large Language Models for Software Engineering
- Foundation Models in Robotics: Applications, Challenges, and the Future
- Model‐based digital twins of medicine dispensers for healthcare IoT applications
- Leveraging Large Language Models to Improve REST API Testing
- EpiTESTER: Testing Autonomous Vehicles with Epigenetic Algorithm and Attention Mechanism
- Evaluating Diverse Large Language Models for Automatic and General Bug Reproduction
- InstOptima: Evolutionary Multi-objective Instruction Optimization via Large Language Model-based Instruction Operators
- Large Language Models for Test-Free Fault Localization
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
- The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)
- Cost Reduction on Testing Evolving Cancer Registry System
- EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
- A Survey of Hallucination in Large Foundation Models
- HITA: An Architecture for System-level Testing of Healthcare IoT Applications
- Large Language Models in Fault Localisation
- Reinforcement Learning for Mutation Operator Selection in Automated Program Repair
- Large Language Models for Software Engineering: Survey and Open Problems
- WizardLM: Empowering large pre-trained language models to follow complex instructions
- Towards Objective-Tailored Genetic Improvement Through Large Language Models
- Language Model Crossover: Variation through Few-Shot Prompting
- Language Model Crossover: Variation through Few-Shot Prompting
- Testing RESTful APIs: A Survey
- GPS: Genetic Prompt Search for Efficient Few-shot Learning
- Search-based Software Testing Driven by Automatically Generated and Manually Defined Fitness Functions
- A Survey on Automated Driving System Testing: Landscapes and Trends
- A Survey on Automated Driving System Testing: Landscapes and Trends
- Causality-based Neural Network Repair
- CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
- NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History
- On the Opportunities and Risks of Foundation Models
- Evaluating Large Language Models Trained on Code
- Learning How to Search: Generating Effective Test Cases Through Adaptive Fitness Function Selection
- Model-based Exploration of the Frontier of Behaviours for Deep Learning\n System Testing
- Pymoo: Multi-Objective Optimization in Python
- Machine Learning Testing: Survey, Landscapes and Horizons
- Machine Learning Testing: Survey, Landscapes and Horizons
- DeepFault: Fault Localization for Deep Neural Networks
- Test suite generation with the Many Independent Objective (MIO) algorithm
- Improving Multi-Objective Test Case Selection by Injecting Diversity in Genetic Algorithms
- A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models
Cited by
Related