#software-engineering6 articles

6 articles

AIBullisharXiv – CS AI · 4h ago2

🧠

From Goals to Aspects, Revisited: An NFR Pattern Language for Agentic AI Systems

Researchers have developed a pattern language methodology to systematically identify and modularize crosscutting concerns in agentic AI systems, addressing issues like security, reliability, and cost management that contribute to high AI project failure rates. The approach uses goal models to discover reusable patterns and implements them through aspect-oriented programming in Rust.

AIBullisharXiv – CS AI · 4h ago2

🧠

SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks

Researchers introduce SWE-Hub, a comprehensive system for generating scalable, executable software engineering tasks for training AI agents. The platform addresses current limitations in AI software development by providing unified environment automation, bug synthesis, and diverse task generation across multiple programming languages.

AIBearisharXiv – CS AI · 4h ago1

🧠

Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement

Research reveals that Large Language Models (LLMs) systematically fail at code review tasks, frequently misclassifying correct code as defective when matching implementations to natural language requirements. The study found that more detailed prompts actually increase misjudgment rates, raising concerns about LLM reliability in automated development workflows.

AINeutralarXiv – CS AI · 4h ago1

🧠

Theory of Code Space: Do Code Agents Understand Software Architecture?

Researchers introduce Theory of Code Space (ToCS), a new benchmark that evaluates AI agents' ability to understand software architecture across multi-file codebases. The study reveals significant performance gaps between frontier LLM agents and rule-based baselines, with F1 scores ranging from 0.129 to 0.646.

AIBullisharXiv – CS AI · 4h ago1

🧠

ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files

Researchers have developed ContextCov, a framework that converts passive natural language instructions for AI agents into active, executable guardrails to prevent code violations. The system addresses 'Context Drift' where AI agents deviate from project guidelines, creating automated compliance checks across static code analysis, runtime commands, and architectural validation.

$COMP

AIBullisharXiv – CS AI · 4h ago1

🧠

FastCode: Fast and Cost-Efficient Code Understanding and Reasoning

Researchers introduce FastCode, a new framework for AI-assisted software engineering that improves code understanding and reasoning efficiency. The system uses structural scouting to navigate codebases without full-text ingestion, significantly reducing computational costs while maintaining accuracy across multiple benchmarks.