Cover Image

Improving Latent Reasoning in LLMs via Soft Concept Mixing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Kang, Duan, Xiangyu, Du, Tianyi
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
by: Zhang, Zhen, et al.
Published: (2025)

RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step
by: Luo, Xiaocheng, et al.
Published: (2026)

On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept
by: Liu, Guangliang, et al.
Published: (2024)

SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs
by: Xu, Yige, et al.
Published: (2025)

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
by: Su, DiJia, et al.
Published: (2025)

Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs
by: Wu, Yang, et al.
Published: (2025)

Geometric Latent Reasoning Induces Shorter Generations in LLMs
by: Kumar, Shashi, et al.
Published: (2026)

Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean
by: Park, Chanwoo, et al.
Published: (2025)

ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement
by: Peng, Xiangyu, et al.
Published: (2024)

Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
by: Du, Hanwen, et al.
Published: (2025)

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
by: Wang, Siyuan, et al.
Published: (2024)

Hybrid Latent Reasoning via Reinforcement Learning
by: Yue, Zhenrui, et al.
Published: (2025)

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
by: Zhang, Xuan, et al.
Published: (2024)

LLM Latent Reasoning as Chain of Superposition
by: Deng, Jingcheng, et al.
Published: (2025)

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
by: Kang, Haoqiang, et al.
Published: (2025)

Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
by: Deng, Jingcheng, et al.
Published: (2026)

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
by: Shi, Dachuan, et al.
Published: (2025)

Impacts of Continued Legal Pre-Training and IFT on LLMs' Latent Representations of Human-Defined Legal Concepts
by: Ho, Shaun
Published: (2024)

Scaling Latent Reasoning via Looped Language Models
by: Zhu, Rui-Jie, et al.
Published: (2025)

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
by: Jiang, Houcheng, et al.
Published: (2026)

LaSR: Context-Aware Speech Recognition via Latent Reasoning
by: Liu, Heyang, et al.
Published: (2026)

Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning
by: Tian, Changyuan, et al.
Published: (2025)

EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States
by: Xu, Hainiu, et al.
Published: (2025)

Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
by: Wang, Chenlong, et al.
Published: (2025)

Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction
by: Han, Kaiqiao, et al.
Published: (2024)

LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking
by: Wu, Junhong, et al.
Published: (2025)

Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates
by: Prakash, Nikhil, et al.
Published: (2025)

Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format
by: Wang, Dingzirui, et al.
Published: (2025)

Benchmarking and Understanding Compositional Relational Reasoning of LLMs
by: Ni, Ruikang, et al.
Published: (2024)

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
by: Zheng, Tong, et al.
Published: (2026)

Latent Concept-based Explanation of NLP Models
by: Yu, Xuemin, et al.
Published: (2024)

Improved Paraphrase Generation via Controllable Latent Diffusion
by: Zou, Wei, et al.
Published: (2024)

Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs
by: Orlicki, José I.
Published: (2025)

MixRea: Benchmarking Explicit-Implicit Reasoning in Large Language Models
by: Cai, Yuanqing, et al.
Published: (2026)

Diversity of Thought Improves Reasoning Abilities of LLMs
by: Naik, Ranjita, et al.
Published: (2023)

Fair In-Context Learning via Latent Concept Variables
by: Bhaila, Karuna, et al.
Published: (2024)

A Survey on Latent Reasoning
by: Zhu, Rui-Jie, et al.
Published: (2025)

Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval
by: Nguyen, Hai-Long, et al.
Published: (2024)

Latent Reasoning via Sentence Embedding Prediction
by: Hwang, Hyeonbin, et al.
Published: (2025)

Latent Visual Reasoning
by: Li, Bangzheng, et al.
Published: (2025)