LatentChem: 从文本思维链到化学推理中的潜在思考
LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
AI总结：
针对化学大语言模型依赖显式思维链导致的模态不匹配问题，提出LatentChem推理接口，通过连续思维向量和动态感知解耦化学逻辑与语言生成，在ChemCoTBench上以59.88%非平局胜率超越强CoT基线，并实现平均10.84倍推理步骤开销降低（5.96倍实际加速）。
摘要：
当前的化学大语言模型主要依赖显式的思维链来解决复杂推理问题。然而，将非语言的隐性化学逻辑强制转化为离散的自然语言，造成了根本性的“模态不匹配”，为推理带来了人为瓶颈。我们提出了LatentChem，一种将化学逻辑与语言生成解耦的推理接口，使模型能够通过连续思维向量和动态感知来处理信息。我们的研究揭示了一个关键涌现行为：自发内化，这里定义为在仅结果优化下的自我选择。当为任务成功进行优化时，模型放弃冗长的文本推导，转而采用隐式的潜在计算，这表明模型将连续流形视为化学逻辑更自然的载体。这一范式转变也被证明是一种更优的计算策略：在严格的ChemCoTBench基准上，LatentChem对强CoT基线取得了59.88%的非平局胜率，同时在所有评估基准上实现了平均10.84倍的推理步骤开销降低（5.96倍实际加速）。我们的结果提供了经验证据，表明化学推理更自然、更有效地实现为连续潜在动力学，而非离散的语言轨迹。
英文摘要：
Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex reasoning problems. However, forcing nonverbal tacit chemical logic into discrete natural language imposes a fundamental ``modality mismatch,'' creating an artificial bottleneck for reasoning. We introduce LatentChem, a reasoning interface that decouples chemical logic from linguistic generation, enabling the model to process information via continuous thought vectors and dynamic perception. Our investigation reveals a pivotal emergent behavior: spontaneous internalization, defined here as self-selected under outcome-only optimization. When optimized for task success, the model abandons verbose textual derivations in favor of implicit latent computation, suggesting that it identifies the continuous manifold as a more native substrate for chemical logic. This paradigm shift also proves to be a superior computational strategy: LatentChem achieves a 59.88\% non-tie win rate against the strong CoT baseline on the rigorous ChemCoTBench, while delivering a broad 10.84$\times$ average reduction in reasoning step overhead (5.96$\times$ wall-clock speedup) across all evaluated benchmarks. Our results provide empirical evidence that chemical reasoning is more naturally and effectively realized as continuous latent dynamics rather than discretized linguistic trajectories.
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。
