Sci-CoE: 通过稀疏监督与几何共识共演化科学推理LLM
Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision
AI总结：
Sci-CoE 通过稀疏监督与几何共识共演化科学推理LLM，提升复杂推理能力与可扩展性。
摘要：
大型语言模型（LLMs）已展示了卓越的推理能力，在代码和数学等领域，共演化范式也展现了 promising 的结果。然而，在科学推理任务中，这些模型仍脆弱，因为解决方案评估不可靠且验证策略多样性有限。在本工作中，我们提出了 Sci-CoE，一种两阶段的科学共演化框架，使模型能够通过从稀疏监督到无监督学习的过渡，自我进化为求解器和验证器。第一阶段中，模型利用少量标注数据建立验证器的基本正确性判断锚点。第二阶段中，我们引入了一种几何奖励机制，共同考虑共识、可靠性和多样性，推动在未标注数据上的大规模自我迭代。在几个通用科学基准上的实验表明，Sci-CoE 提高了复杂推理能力，表现出强大的可扩展性，有助于构建更稳健和多样化的评估系统。代码可在 https://github.com/InternScience/Sci-CoE 上获得。
英文摘要：
Large language models (LLMs) have demonstrated exceptional reasoning capabilities, and co-evolving paradigms have shown promising results in domains such as code and math. However, in scientific reasoning tasks, these models remain fragile due to unreliable solution evaluation and limited diversity in verification strategies. In this work, we propose Sci-CoE, a two-stage scientific co-evolving framework that enables models to self-evolve as both solver and verifier through a transition from sparse supervision to unsupervised learning. In the first stage, the model uses a small set of annotated data to establish fundamental correctness judgment anchors for the Verifier. In the second stage, we introduce a geometric reward mechanism that jointly considers consensus, reliability, and diversity, driving large-scale self-iteration on unlabeled data. Experiments on several general scientific benchmarks demonstrate that Sci-CoE enhances complex reasoning capabilities and exhibits strong scalability, facilitating the construction of more robust and diverse evaluation systems. Codes are available at https://github.com/InternScience/Sci-CoE.
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。
