让大模型自动选最合适的推理方式，提升数学与逻辑题解题准确率。
Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem Routing
- 根据题目类型动态切换三种专用推理模式，精准匹配问题特点。
- 在GSM8K上达71.5%准确率，比最强基线高1.0个百分点。
- 无需训练即可部署，适合追求高效高精度推理的应用场景。
我们提出链式模拟（Chain of Simulation, CoS），一种新型双模式推理框架，可动态将问题路由至大语言模型（LLM）中的专用推理策略。不同于现有统一提示方法，CoS采用三种不同推理模式：(1) 数学问题使用带自一致性校验的计算流程；(2) 空间推理任务通过JSON格式的符号状态追踪；(3) 多跳推理采用混合事实抽取。在GSM8K、StrategyQA和bAbI基准上，使用四个先进模型（Gemma-3 27B、LLaMA-3.1 8B、Mistral 7B、Qwen-2.5 14B）进行综合评估，结果显示CoS在GSM8K上达到71.5%准确率（绝对提升1.0%），StrategyQA上90.0%（提升2.5%），bAbI上19.0%（相对提升65.2%）。分析表明，问题特定模式选择至关重要：正确应用计算模式时数学题准确率达81.2%，错误路由则为0%。本文提供模式选择、状态追踪与答案提取的详细算法，证明CoS可在不增加训练成本的前提下显著提升推理能力。相比自一致性方法，CoS在保持相当性能的同时，计算成本降低54%。
原文摘要 · Abstract (English)
We present Chain of Simulation (CoS), a novel dual-mode reasoning framework that dynamically routes problems to specialized reasoning strategies in Large Language Models (LLMs). Unlike existing uniform prompting approaches, CoS employs three distinct reasoning modes: (1) computational flow with self-consistency for mathematical problems, (2) symbolic state tracking with JSON representations for spatial reasoning, and (3) hybrid fact-extraction for multi-hop inference. Through comprehensive evaluation on GSM8K, StrategyQA, and bAbI benchmarks using four state-of-the-art models (Gemma-3 27B, LLaMA-3.1 8B, Mistral 7B, and Qwen-2.5 14B), we demonstrate that CoS achieves 71.5% accuracy on GSM8K (1.0% absolute improvement), 90.0% on StrategyQA (2.5% improvement), and 19.0% on bAbI (65.2% relative improvement) compared to the strongest baselines. The analysis reveals that problem-specific mode selection is crucial, with computational mode achieving 81.2% accuracy when correctly applied to mathematical problems, while misrouting leads to 0% accuracy. We provide detailed algorithms for mode selection, state tracking, and answer extraction, establishing CoS as an effective approach for improving LLM reasoning without additional training. The framework provides superior trade-offs between accuracy and efficiency compared to Self-Consistency, achieving comparable performance at 54% lower computational cost.
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。