用简单提示词协调多个大模型，自动过滤有害代码修改。
SLEAN: Simple Lightweight Ensemble Analysis Network for Multi-Provider LLM Coordination: Design, Implementation, and Vibe Coding Bug Investigation Case Study
- 通过三阶段流程：分析、互评、仲裁，用文本模板协调多模型。
- 在15个漏洞中筛选出22个安全修复，减少90%的代码改动范围。
- 无需编程知识即可部署，适合安全审计与文档验证场景。
我们提出SLEAN（Simple Lightweight Ensemble Analysis Network），一种基于文本提示编排的确定性框架，用于协调多个大模型提供者。不同于需要专用基础设施的复杂多智能体系统，SLEAN仅通过.txt模板作为提示桥接，无需技术背景即可部署。其三阶段协议包括独立分析、交叉批判和仲裁，可有效过滤生产前的有害代码建议，解决AI辅助调试引入冗余复杂性、破坏原有功能或误解决问题的问题。评估15个软件漏洞时，分析了69个AI生成的修复方案。SLEAN的过滤机制成功接受22个修复（31.9%，95%置信区间20.9-42.9%），拒绝47个若直接应用将造成危害的方案。仲裁过程使代码变更范围相较原始输出减少83%-90%，强调最小因果修改而非扩展范围。轻量级输入（类型2）比详细输入（类型1）更高效，每接受一个修复分别需2.85与3.56个提案（接受率分别为35.1%与28.1%），效率提升约20%。各模型间高一致性（至少80%）仅出现在4/15案例中，且仅带来2.4个百分点的接受率提升；仲裁仅在恰好10%一致性下出现于2/15案例，但低一致性本身并不必然触发仲裁。该文件驱动、提供者无关的架构实现无编码部署，适用于安全审计、代码审查、文档验证等需可靠多源合成与端到端可追溯性的领域。
原文摘要 · Abstract (English)
We present SLEAN (Simple Lightweight Ensemble Analysis Network), a deterministic framework for coordinating multiple LLM providers through text-based prompt orchestration. Unlike complex multi-agent systems requiring specialized infrastructure, SLEAN operates as a simple prompt bridge between LLMs using .txt templates, requiring no deep technical knowledge for deployment. The three-phase protocol formed by independent analysis, cross-critique, and arbitration, filters harmful AI-generated code suggestions before production deployment, addressing how AI-assisted debugging increasingly produces modifications that introduce unnecessary complexity, break existing functionality, or address problems. Evaluating 15 software bugs, we analyzed 69 AI-generated fix propositions. SLEAN's filtering accepted 22 fixes (31.9%, 95% CI 20.9-42.9%) while rejecting 47 that would have been harmful if applied verbatim. The arbitration process reduced code change surface by 83-90% relative to raw AI outputs, enforcing minimal causal edits over scope-expanding modifications. Minimal Type 2 inputs proved more efficient than detailed Type 1 inputs, requiring 2.85 versus 3.56 propositions per accepted fix (35.1% versus 28.1% acceptance, about a 20% efficiency gain). Agreement between AI systems showed weak correlation with fix quality: high convergence (at least 80%) occurred in 4 of 15 cases and improved acceptance by only 2.4% points; arbitration appeared only at exactly 10% convergence in 2 of 15 cases, although low convergence alone did not necessitate arbitration. The file-driven, provider-agnostic architecture enables deployment without specialized coding expertise, making it applicable to security auditing, code review, document verification, and other domains requiring reliable multi-provider synthesis with end-to-end auditability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。