The field of software engineering is witnessing significant advancements with the integration of Large Language Models (LLMs). Current developments indicate a shift towards leveraging LLMs for various tasks such as debugging, test generation, and code comprehension. Researchers are exploring the potential of LLMs in improving the efficiency and effectiveness of software development processes. Noteworthy papers in this area include 'Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failures', which proposes a hierarchical knowledge management framework for debugging, and 'Synthesizing Precise Protocol Specs from Natural Language for Effective Test Generation', which presents a two-stage pipeline for generating formal protocol specifications from natural language. These innovative approaches highlight the promising future of LLMs in software engineering.
Advancements in Large Language Models for Software Engineering
Sources
Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failures
Synthesizing Precise Protocol Specs from Natural Language for Effective Test Generation
MASTEST: A LLM-Based Multi-Agent System For RESTful API Tests
Can Large Language Models Solve Path Constraints in Symbolic Execution?
End-to-End Automated Logging via Multi-Agent Framework
LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs
Generating Reading Comprehension Exercises with Large Language Models for Educational Applications
Can LLMs Recover Program Semantics? A Systematic Evaluation with Symbolic Execution
LLMs-Powered Real-Time Fault Injection: An Approach Toward Intelligent Fault Test Cases Generation
LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework
Hierarchical Evaluation of Software Design Capabilities of Large Language Models of Code
Empirical Assessment of the Code Comprehension Effort Needed to Attack Programs Protected with Obfuscation
Large Language Models for Unit Test Generation: Achievements, Challenges, and the Road Ahead