研究人员开发了DiscoLoop，一种新颖的循环架构，旨在增强大型语言模型的多跳推理能力。标准的Transformer在跨越多个推理步骤时难以保留信息，而“深度局部存储”问题加剧了这一问题。DiscoLoop通过在其循环结构中同时纳入离散嵌入和连续隐藏状态来解决这个问题。这种双通道方法显著提高了多跳推理任务的准确性并缩短了训练时间，并有望用于实际的语言模型预训练。 AI
影响 DiscoLoop的架构可以提高LLM的推理能力，可能导致更复杂的AI代理和在复杂任务上更好的性能。
排序理由 研究论文，详细介绍了用于多跳推理的新模型架构。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.00341v1 Announce Type: cross Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). However, many questions require the model to internalize the multi-step reasoning w…
Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). However, many questions require the model to internalize the multi-step reasoning within a single forward pass before generating the …