• 4D-ARE: Bridging the Attribution Gap in LLM Agent Requirements Engineering
• A First Look at Coding Agents’ Compliance with AI Contribution Rules in Open-Source Communities
• A Roadmap for Modern Code Review: Challenges and Opportunities
• A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)
• A Survey of Code Review Benchmarks and Evaluation Practices in Pre-LLM and LLM Era
• A Survey of Vibe Coding with Large Language Models
• A Survey on Code Generation with LLM-based Agents
• A Survey on Evaluation of LLM-based Agents
• ACEM: A Cost Estimation Model for Agentic Software Engineering
• Adoption and Impact of Command-Line AI Coding Agents
• Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey
• Agent READMEs: An Empirical Study of Context Files for Agentic Coding
• Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-Based Agents
• Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
• AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
• Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development
• Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering
• Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
• Agentic coding and persistent returns to expertise
• Agentic Design Patterns: A System-Theoretic Framework
• Agentic Much? Adoption of Coding Agents on GitHub
• Agentic Software Engineering: Foundational Pillars and a Research Roadmap
• Agentic Software Issue Resolution with Large Language Models: A Survey
• Agentic Software: How AI Agents Are Restructuring the Software Paradigm
• Agentic Tool Use in Large Language Models: A Survey
• AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling
• Agentless: Demystifying LLM-based Software Engineering Agents
• AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
• AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
• AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
• AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities
• Desarrollo de software asistido por IA para profesionales con formaciones diversas
• AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development
• AI-powered Code Review with LLMs: Early Results
• AI-to-AI Code Reviews of GitHub Pull Requests
• AI Writes Faster Than Humans Can Review: A Longitudinal Study of an Enterprise “2×” Mandate
• AIDev: Studying AI Coding Agents on GitHub
• An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors
• Are AI-assisted Development Tools Immune to Prompt Injection?
• Are Coding Agents Generating Over-Mocked Tests? An Empirical Study
• Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement
• Are We All Using Agents the Same Way? An Empirical Study of Core and Peripheral Developers Use of Coding Agents
• Assistance to Autonomy: A Systematic Literature Review of Agentic AI across the Software Development Life Cycle
• AutoCodeRover: Autonomous Program Improvement
• AutoDev: Automated AI-Driven Development
• Automated Code Review In Practice
• Automated Code Review Using Large Language Models at Ericsson: An Experience Report
• BitsAI-CR: Automated Code Review via LLM in Practice
• Building an Internal Coding Agent at Zup: Lessons and Open Questions
• Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
• Building Software by Rolling the Dice: A Qualitative Study of Vibe Coding
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• ChatDev: Communicative Agents for Software Development
• Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering
• ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification
• Code as Agent Harness: Toward Executable, Verifiable, and Stateful Agent Systems
• Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering
• Code Review Agent Benchmark
• CodePlan: Repository-level Coding using LLMs and Planning
• Codified Context: Infrastructure for AI Agents in a Complex Codebase
• Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering
• Comprehension Debt in GenAI-Assisted Software Engineering Projects
• A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
• Context as a Tool: Context Management for Long-Horizon SWE-Agents
• Context Before Code: An Experience Report on Vibe Coding in Practice
• CoverUp: Effective High Coverage Test Generation for Python
• DeepCode: Open Agentic Coding
• Dive into Claude Code: The Design Space of Today’s and Future AI Agent Systems
• DocsChisel: Adaptive Tool Documentation Optimization Framework for LLM Agents
• Empowering Agile-Based Generative Software Development through Human-AI Teamwork
• Engineering Pitfalls in AI Coding Tools: An Empirical Study of Bugs in Claude Code, Codex, and Gemini CLI
• Enhancing Formal Software Specification with Artificial Intelligence
• Evaluation and Benchmarking of LLM Agents: A Survey
• Executable Code Actions Elicit Better LLM Agents
• Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
• Faster Code, Deeper Debt? A Multivocal Literature Review on Technical Debt and Its Early Signs in LLM-Assisted Software Development
• FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
• From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence
• From Code to Contract: Spec-Driven Development in the Age of AI Coding Assistants
• From Determinism to Delegation: AI-Native Software Engineering and the Evolution of the Agentic Engineer
• From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality
• From Industry Claims to Empirical Reality: An Empirical Study of Code Review Agents in Pull Requests
• From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
• Desde los Obstáculos hasta las Estrategias: Integración de la inteligencia artificial en el ciclo de vida del desarrollo del software
• From Prompt to Process: a Process Taxonomy and Comparative Assessment of Frameworks Supporting AI Software Development Agents
• From Tool Orchestration to Code Execution: A Study of MCP Design Choices
• An Empirical Study of Generative AI Adoption in Software Engineering
• Grounding AI Agents in Contracts: An Empirical Evaluation of Spec-Driven Test Generation
• Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents — A Source-Code Study of Eleven Systems
• Harness Engineering for Agentic AI Coding Tools: An Exploratory Study
• How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests
• How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
• How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests
• Human-AI Experience in Integrated Development Environments: A Systematic Literature Review
• Human-In-the-Loop Software Development Agents
• The Impact of AI Coding Assistants on Software Engineering: A Longitudinal Study
• Impact of LLM-based Review Comment Generation in Practice: A Mixed Open-/Closed-source User Study
• Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives
• Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
• Instruction-Following Evaluation in Function Calling for Large Language Models
• InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
• Is Agentic Code Review Helpful? Mining Developers’ Feedback to CodeRabbit Reviews in the Wild
• Is Self-Repair a Silver Bullet for Code Generation?
• The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
• Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
• Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• LlamaFirewall: An open source guardrail system for building secure AI agents
• LLM Agents Already Know When to Call Tools - Even Without Reasoning
• LLM Agents Making Agent Tools
• LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
• LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead
• LLM4TDD: Best Practices for Test Driven Development Using Large Language Models
• Loop Engineering: Building Blocks, Adoption, and Impact
• LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation
• Magentic-UI: Towards Human-in-the-loop Agentic Systems
• MarsCode Agent: AI-native Automated Bug Fixing
• MASAI: Modular Architecture for Software-engineering AI Agents
• MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
• MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark
• MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers
• Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity
• Mise en Place for Agentic Coding: Deliberate Preparation as Context Engineering Methodology
• Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
• NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
• Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
• On the Impact of AGENTS.md Files on the Efficiency of AI Coding Agents
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents
• Professional Software Developers Don’t Vibe, They Control: AI Agent Use for Coding in 2025
• Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
• ReAct: Synergizing Reasoning and Acting in Language Models
• Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering
• Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery
• RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
• Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review
• Rethinking Code Review Workflows with LLM Assistance: An Empirical Study
• Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study
• SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
• SDAD: Spec-Driven Agentic Development for the AI-Native SDLC
• Specification-Driven Development as the Foundation of AI-Native Enterprise Software Engineering
• Practical Implementation Report on Introducing Spec-Driven Development Using AI Agents in Software Development PBL
• ソフトウェア開発PBLへのAIエージェントを活用した仕様駆動開発の導入実践報告
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• Software Delegation Contracts: Measuring Reviewability in AI Coding-Agent Work
• Software Engineering in the Agent Era: From Trustworthy Change to Human–Agent Software Organizations
• Spec-Driven Development for Agentic Software Engineering: Harnessing Human–Agent Teamwork
• Spec Kit Agents: Context-Grounded Agentic Workflows
• SpecGen: Automated Generation of Formal Program Specifications via Large Language Models
• Specification-Driven DevOps for Multi-Service Environments
• SpecRover: Code Intent Extraction via LLMs
• Stop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step Prompting
• StruQ: Defending Against Prompt Injection with Structured Queries
• From Question Answering to Task Completion: A Survey on Agent System and Harness Design
• A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
• SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?
• SWE-Bench+: Enhanced Coding Benchmark for LLMs
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• SWE-chat: Coding Agent Interactions From Real Users in the Wild
• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
• SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
• SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review
• Teaching Large Language Models to Self-Debug
• A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions
• Test-Driven Development for Code Generation
• A Framework for Testing and Adapting REST APIs as LLM Tools
• The Bitter Lesson of Tool Calling
• The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
• The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
• The Impact of Large Language Models (LLMs) on Code Review Process
• The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering
• The Role Specialization Model (RSM): Coordinating LLM-Based Tools in Agentic Software Development - An Exploratory Case Study
• The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE
• The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development
• These Aren’t the Reviews You’re Looking For: How Humans Review AI-Generated Pull Requests
• ToolACE: Winning the Points of LLM Function Calling
• Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary
• Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap
• Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
• TraceLab: Characterizing Coding Agent Workloads for LLM Serving
• Trustworthy AI Software Engineers
• UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
• Vibe Coding Kills Open Source
• Vibe Coding in Software Development: A Multivocal Literature Review
• Vibe Coding: Practice, Performance, Productivity, and Risk—A State-of-the-Art Review
• Vibe coding: programming through conversation with artificial intelligence
• Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
• Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
• Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
• Why Software Engineering Is Indispensable in the Age of Coding Agents
• “Your AI, My Shell”: Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
• “You’re Right, Let Me Fix It”: How LLM Agents Damage Correct Work When Falsely Accused