用双系统架构提升图着色求解速度与准确率
A Neurosymbolic Fast and Slow Architecture for Graph Coloring
- 结合快思（LLM）慢思（符号推理）双系统，动态调度求解
- 比传统符号求解器成功率高10.5%，速度最快快30%
- 适合需要高精度与高效求解的约束问题场景
约束满足问题（CSP）因复杂约束和精确解要求对人工智能构成挑战。现有符号求解器通常较慢，而大语言模型（LLMs）单独处理此类问题表现不佳。为此，我们基于SOFAI_v1架构，引入改进的元认知治理机制，提出SOFAI_v2。该架构融合快速系统1（利用LLM）与缓慢系统2（受元认知模块控制），系统1生成初始解，通过元认知反馈与示例优化以更好满足约束；若系统1失败，则元认知主动调用系统2确保正确性。实验证明，SOFAI_v2在图着色问题上成功率达10.5%更高，且最快比传统符号求解器快30%。
原文摘要 · Abstract (English)
Constraint Satisfaction Problems (CSPs) present significant challenges to artificial intelligence due to their intricate constraints and the necessity for precise solutions. Existing symbolic solvers are often slow, and prior research has shown that Large Language Models (LLMs) alone struggle with CSPs because of their complexity. To bridge this gap, we build upon the existing SOFAI architecture (SOFAI_v1), which adapts Daniel Kahneman's ''Thinking, Fast and Slow'' cognitive model to AI. Our enhanced architecture, SOFAI_v2, integrates refined metacognitive governance mechanisms to improve adaptability across complex domains, specifically tailored here for solving the graph coloring problem, a specific type of CSP. SOFAI_v2 combines a fast System 1 (S1), leveraging LLMs, with a deliberative System 2 (S2), governed by a metacognition module. S1's initial solutions, often limited by constraint adherence issues, are improved through targeted feedback and examples from metacognition, aligning S1 more closely with CSP requirements. If S1 fails to resolve the problem, metacognition strategically invokes S2, ensuring accurate and reliable solutions. Our empirical results demonstrate that SOFAI_v2 achieves a 10.5% higher success rate and is up to 30% faster than a traditional symbolic solver in solving graph coloring problems.
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。