CRAB-Bench and RUSE create a new evaluation framework for LLM agents on constraint-graph tasks with realistic human-like user behaviors, reporting 61% pass@1 for the best model and up to 57% further drops under RUSE.
hub
Vibe coding vs
14 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
14
Pith papers citing it
3
external citations · Pith
abstract
This review presents a comprehensive analysis of two emerging paradigms in AI-assisted software development: vibe coding and agentic coding. While both leverage large language models (LLMs), they differ fundamentally in autonomy, architectural design, and the role of the developer. Vibe coding emphasizes intuitive, human-in-the-loop interaction through prompt-based, conversational workflows that support ideation, experimentation, and creative exploration. In contrast, agentic coding enables autonomous software development through goal-driven agents capable of planning, executing, testing, and iterating tasks with minimal human intervention. We propose a detailed taxonomy spanning conceptual foundations, execution models, feedback loops, safety mechanisms, debugging strategies, and real-world tool ecosystems. Through comparative workflow analysis and 20 detailed use cases, we illustrate how vibe systems thrive in early-stage prototyping and education, while agentic systems excel in enterprise-grade automation, codebase refactoring, and CI/CD integration. We further examine emerging trends in hybrid architectures, where natural language interfaces are coupled with autonomous execution pipelines. Finally, we articulate a future roadmap for agentic AI, outlining the infrastructure needed for trustworthy, explainable, and collaborative systems. Our findings suggest that successful AI software engineering will rely not on choosing one paradigm, but on harmonizing their strengths within a unified, human-centered development lifecycle.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SaaSBench introduces a heterogeneous benchmark for enterprise SaaS engineering and shows that state-of-the-art coding agents fail over 95% of the time before reaching deep business logic due to setup and integration problems.
Copilot boosts performance in brownfield tasks but decouples from comprehension unless users actively verify generated code, with verification frequency predicting understanding at r=0.96.
Changing only the prompter's age and gender in AI coding prompts produces statistically significant differences in generated website interface design, template content, and code structure across 800 generated websites and a 20-person user study.
LLMs generate verifiable MaxSAT encodings from natural language, achieving over 80% acceptance rates on preference tasks where direct LLM reasoning fails.
A repository-level AGENTS.md governance framework with commit-level AI disclosure, session logging, pre-commit gates, and mandatory human review is demonstrated on two new TMAP8 validation cases.
AI-generated security pull requests frequently contain a small set of recurring weaknesses, with many flawed ones merged and rejections driven by process factors rather than technical issues.
Concurrent human-agent interactions occur in 31.8% of turns and follow five action patterns explained by six triggers and four enabling factors, enabled by a context-aware design probe called CLEO.
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
An AI-native TDD framework operationalizes classical TDD principles as prompt-level and workflow-level governance mechanisms in a layered multi-agent architecture to improve stability and reproducibility of LLM code generation.
Organizational policies constrain agency in AI-mediated software engineering more than individual preferences, with seniors using detailed delegation and pre-AI instincts while juniors oscillate between over-reliance and avoidance.
Proposes five foundational pillars and architectural patterns for building robust GenAI-native systems by combining AI with software engineering principles.
Vibe coding enables clinicians to prototype digital health tools by prompting LLMs in natural language, democratizing bespoke software development.
citing papers explorer
-
CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation
CRAB-Bench and RUSE create a new evaluation framework for LLM agents on constraint-graph tasks with realistic human-like user behaviors, reporting 61% pass@1 for the best model and up to 57% further drops under RUSE.
-
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
SaaSBench introduces a heterogeneous benchmark for enterprise SaaS engineering and shows that state-of-the-art coding agents fail over 95% of the time before reaching deep business logic due to setup and integration problems.
-
Code Comprehension with GitHub Copilot: Performance Gains, Comprehension Trade-offs, and Behavioral Predictors in Brownfield Programming
Copilot boosts performance in brownfield tasks but decouples from comprehension unless users actively verify generated code, with verification frequency predicting understanding at r=0.96.
-
Biased or Personalized? The Impact of Personal Information on AI-driven Development
Changing only the prompter's age and gender in AI coding prompts produces statistically significant differences in generated website interface design, template content, and code structure across 800 generated websites and a 20-person user study.
-
Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability
LLMs generate verifiable MaxSAT encodings from natural language, achieving over 80% acceptance rates on preference tasks where direct LLM reasoning fails.
-
Bridging the Gap on AI-Assisted Scientific Software Development Through Transparency and Traceability
A repository-level AGENTS.md governance framework with commit-level AI disclosure, session logging, pre-commit gates, and mandatory human review is demonstrated on two new TMAP8 validation cases.
-
Insights into Security-Related AI-Generated Pull Requests
AI-generated security pull requests frequently contain a small set of recurring weaknesses, with many flawed ones merged and rejections driven by process factors rather than technical issues.
-
"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction
Concurrent human-agent interactions occur in 31.8% of turns and follow five action patterns explained by six triggers and four enabling factors, enabled by a context-aware design probe called CLEO.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
-
PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
-
TDD Governance for Multi-Agent Code Generation via Prompt Engineering
An AI-native TDD framework operationalizes classical TDD principles as prompt-level and workflow-level governance mechanisms in a layered multi-agent architecture to improve stability and reproducibility of LLM code generation.
-
From Junior to Senior: Allocating Agency and Navigating Professional Growth in Agentic AI-Mediated Software Engineering
Organizational policies constrain agency in AI-mediated software engineering more than individual preferences, with seniors using detailed delegation and pre-AI instincts while juniors oscillate between over-reliance and avoidance.
-
Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems
Proposes five foundational pillars and architectural patterns for building robust GenAI-native systems by combining AI with software engineering principles.
-
Vibe coding for clinicians: democratising bespoke software development for digital health innovation
Vibe coding enables clinicians to prototype digital health tools by prompting LLMs in natural language, democratizing bespoke software development.