1
Implicit Reasoning Steering via Concept Chaining
利用概念链引导大模型进行隐式推理，为提升推理可控性提供新思路
arXiv:2607.14242v1 Announce Type: new Abstract: Large language models often appear to reason reliably, yet on many questions repeated sampling yields …
2
Latent Thought Flow: Efficient Latent Reasoning in Large Language Models
新方法让大模型在潜在空间高效推理，大幅降低计算开销，提升效率。
arXiv:2606.16222v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly rely on intermediate reasoning, yet explicit Chain-of-Though…
3
Implicit Reasoning for Large Language Model-based Generative Recommendation
揭开隐式推理如何激活大模型预训练知识，为生成式推荐注入新思路。
arXiv:2606.14142v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR…
4
LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
化学LLM推理迎来革新：用隐式思考（Latent Thinking）替代传统CoT，打破语言与化学逻辑的模态不匹配瓶颈
arXiv:2602.07075v5 Announce Type: replace-cross Abstract: Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Though…
5
MixRea: Benchmarking Explicit-Implicit Reasoning in Large Language Models
新基准MixRea评估LLM在显式与隐式推理上的表现，揭示推理能力的短板。
arXiv:2605.20128v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into high-stakes decision-making. Inspired by…