InCoder-32B-Thinking：工业代码世界模型用于推理
InCoder-32B-Thinking: Industrial Code World Model for Thinking
AI总结：
本文提出InCoder-32B-Thinking，通过工业代码世界模型生成推理轨迹，评估显示其在通用和工业基准上均取得领先开源结果。
摘要：
工业软件开发在芯片设计、GPU优化和嵌入式系统领域缺乏专家推理轨迹，展示工程师如何处理硬件约束和时序语义。本文提出InCoder-32B-Thinking，基于Error-driven Chain-of-Thought（ECoT）合成框架和工业代码世界模型（ICWM）训练生成推理轨迹。ECoT通过多轮对话中的思考内容合成推理链，并显式建模错误纠正过程。ICWM基于领域特定的执行轨迹训练，学习代码如何影响硬件行为的因果动态，并通过预测执行结果前的自我验证。所有合成的推理轨迹通过领域工具链验证，生成匹配工业任务自然推理深度分布的训练数据。在14个通用（81.3%在LiveCodeBench v5）和9个工业基准（84.0%在CAD-Coder和38.0%在KernelBench）上评估，InCoder-32B-Thinking在所有领域均取得顶级开源结果。GPU优化
英文摘要：
Industrial software development across chip design, GPU optimization, and embedded systems lacks expert reasoning traces showing how engineers reason about hardware constraints and timing semantics. In this work, we propose InCoder-32B-Thinking, trained on the data from the Error-driven Chain-of-Thought (ECoT) synthesis framework with an industrial code world model (ICWM) to generate reasoning traces. Specifically, ECoT generates reasoning chains by synthesizing the thinking content from multi-turn dialogue with environmental error feedback, explicitly modeling the error-correction process. ICWM is trained on domain-specific execution traces from Verilog simulation, GPU profiling, etc., learns the causal dynamics of how code affects hardware behavior, and enables self-verification by predicting execution outcomes before actual compilation. All synthesized reasoning traces are validated through domain toolchains, creating training data matching the natural reasoning depth distribution of industrial tasks. Evaluation on 14 general (81.3% on LiveCodeBench v5) and 9 industrial benchmarks (84.0% in CAD-Coder and 38.0% on KernelBench) shows InCoder-32B-Thinking achieves top-tier open-source results across all domains.GPU Optimization
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
