研究库 论文知识库

内容库 / 论文

arXiv:2610.06666 · LLM 基础设施

What Matters for Latent Reasoning with Flow Matching

What Matters for Latent Reasoning with Flow Matching

类型：arxiv
标识：2610.06666
链接：https://arxiv.org/abs/2610.06666
主分类：llm-infra
形态：method
TLDR：Latent reasoning lets a large language model (LLM) think in a continuous space and verbalize only the answer. We argue that an effective latent thought must meet five requirements: it should be useful, helping produce the correct answer rather than merely changing it, diverse, so that resampling yields different reasoning trajectories, explainable, so that a decoded chain of thought (CoT) reflects reasoning the answer actually follows, refinable with more inference compute, and efficient, costing less than an explicit CoT at comparable accuracy. Current methods rarely meet these requirements:
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-06-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

仓库 griver/Q-RAG

笔记 KVAE Tokenizers arXiv:2608.05798 · multimodal · 精读与批判 v2

笔记精读笔记：Characterizing State Space Model and Hybrid Language Model Performance with Long Context

笔记 2026-07-04 上午多模态对照精读 · Seeker（文本→像素的长上下文 MLLM）

仓库 leon2k2k2k/llm-feedback-alignment

文档 Tom-on-flyP-2026-07-25

arXiv

2610.06666

TLDR

Latent reasoning lets a large language model (LLM) think in a continuous space and verbalize only the answer. We argue that an effective latent thought must meet five requirements: it should be useful, helping produce the correct answer rather than merely changing it, diverse, so that resampling yields different reasoning trajectories, explainable, so that a decoded chain of thought (CoT) reflects reasoning the answer actually follows, refinable with more inference compute, and efficient, costing less than an explicit CoT at comparable accuracy. Current methods rarely meet these requirements:

arXiv ↗ 中文全文