将科学计算经验转化为可迁移的流程知识，提升模型持续学习能力。
From Execution to Capability: Scientific Experience Consolidation via Procedural Knowledge Synthesis
- 通过对比成功与失败案例，提炼跨任务通用计算流程
- 9B模型在流程引导下性能提升5.62/11.25点，验证知识迁移有效性
- 适合追求模型长期进化与科学计算自动化的研究者
大语言模型日益胜任科学计算任务，但单次问题的可执行反馈难以转化为持久能力。本文研究科学计算经验整合：将已验证的运行经验转化为可迁移的程序化知识并实现模型持续改进。该任务面临两大挑战：轨迹生成的成果可能包含源任务特异性修复而非跨任务计算机制；弱化的目标模型可能无法执行有效抽象，形成抽象-执行鸿沟。为此，提出SciConsolidate，通过对比验证的成功与失败案例推导跨任务程序，经开发-验证门控筛选，并利用故障驱动、无答案的查询生成扩展数据集，无需预设参考答案。因目标模型可能无法直接执行这些抽象，采用更强模型将其具象化为可执行代码监督，用于标准无流程SFT训练；同时设立无流程教师分支，隔离流程指导价值。在SciCode数据集上，运行时程序注入使Qwen3.6-27B提升3.85/6.26子步骤/主问题得分，但对Qwen3.5-9B几乎无增益，实证了抽象-执行鸿沟存在。经流程引导具象化后，9B学生模型在无流程部署下相比无流程SFT控制组提升3.89/6.25分，相比原始9B模型提升5.62/11.25分。结果确立了科学计算中经验到能力的转化路径，为自提升科学助手提供实用起点。
原文摘要 · Abstract (English)
Large language models increasingly solve scientific-computing tasks, but executable feedback from one problem rarely becomes durable capability on subsequent problems. We study scientific-computing experience consolidation: converting verified runtime experience into transferable procedural knowledge and persistent model improvement. This setting presents two challenges: trajectory-derived artifacts may encode source-specific repairs rather than cross-task computational mechanisms; and a weaker target model may be unable to operationalize an otherwise valid abstract procedure - an abstraction-execution gap. We introduce SciConsolidate, which contrasts verified successes and failures to induce cross-task procedures, selects them through a development-validation gate, and uses failure-informed, answer-free query synthesis to expand the consolidation data without requiring pre-existing reference answers. Because the target model may not directly execute these abstractions, a stronger model concretizes them into executable code supervision for standard, procedure-free SFT; a matched no-procedure teacher branch isolates the value of procedural guidance. On SciCode, runtime procedure injection improves Qwen3.6-27B by +3.85/+6.26 sub-step/main-problem points, but yields almost no aggregate main-problem gain for Qwen3.5-9B, providing operational evidence of the abstraction-execution gap. After procedure-guided concretization, the 9B student improves under procedure-free deployment by +3.89/+6.25 points over the no-procedure SFT control and by +5.62/+11.25 over the original 9B model. These results establish an experience-to-capability pathway for scientific computing and provide a practical starting point for scaling self-improving scientific assistance.
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。