MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration

arXiv:2608.25457 · cs.CR, cs.AI, cs.MA · Submitted 2026-08-26 · Read on arXiv

cs.CR, cs.AI, cs.MA

Submitted: 2026-08-26

Updated: 2026-09-02

Comments: 8 pages

Code: https://github.com/Mishuni/macgen-secure-code

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 16× in this paper · explained in 2 episodes
• Knowledge Base — 8× in this paper
• Verification — 7× in this paper · explained in 2 episodes
• RAG — 6× in this paper · explained in 3 episodes
• Core — 5× in this paper · explained in 2 episodes
• Multi-Agent Framework — 5× in this paper · explained in 3 episodes
• Iterative Refinement — 4× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Analyzer — 2× in this paper · explained in 1 episode
• Computational overhead — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• OWASP Application Security Verification Standard — 2× in this paper
• AI Foundation Model — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Application Programming Interface — 1× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Common Weakness Enumeration — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Knowledge Base Construction — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Recursive Critic and Improvement — 1× in this paper
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation — 1× in this paper
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes

Sources

• Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
• Evaluating Large Language Models Trained on Code
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
• GPT-4o System Card
• Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
• AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
• ChatDev: Communicative Agents for Software Development
• jina-embeddings-v3: Multilingual Embeddings With Task LoRA
• Qwen3 Technical Report

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs