Continuous Latent Reasoning

Follow this topic Ask about this topic

Continuous latent reasoning asks whether language and multimodal models can solve problems by updating internal representations rather than generating a word-by-word chain of thought, potentially reducing latency and token use. Approaches include recurrent or looped latent rollouts, learned latent prefixes, flow- and diffusion-based trajectories, reinforcement learning, and adaptive rules for how long to think. These methods are tested on arithmetic, Sudoku and maze planning, code generation, visual reasoning, audio tasks, and tool-using agents, with reported gains in efficiency and sometimes accuracy over explicit reasoning. A central open tension is whether compact latent states faithfully support the answer: accuracy alone does not establish this, and causal analyses find shortcut behavior while robustness, supervision, and reliable decoding remain challenges.

Latest papers

80 papers26 papers in the last four weeks, up 189% on the four weeks before. 0.2% of all new papers.

Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
Apr 30, 2026Jingcheng Deng, Zihao Wei, Liang Pang +4Reinforcement Learning RL for Language Model Reasoning
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences
Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
Apr 20, 2026Jinghui Lu, Jiayi Guan, Zhijian Huang +47Trajectory Generation VLMs for Autonomous Driving
LEPO: Latent Reasoning Policy Optimization for Large Language Models
Apr 20, 2026Yuyan Zhou, Jiarui Yu, Hande Dong +4Reinforcement Learning RL for Language Model Reasoning
Tencent · Zhejiang University · Shanghai Jiao Tong University
Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
Apr 12, 2026Yudong Han, Yong Wang, Zaiquan Yang +3Latent Visual Reasoning Continuous Latent Reasoning
Beijing Institute of Technology · AMAP, Alibaba Group · City University of Hong Kong +2
SeLaR: Selective Latent Reasoning in Large Language Models
Apr 9, 2026Renyu Fu, Guibo LuoCoT Reasoning Continuous Latent Reasoning
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology Shenzhen Graduate School, Peking University
The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
Apr 7, 2026Michael Rizvi-Martel, Guillaume Rabusseau, Marius MosbachContinuous Latent Reasoning LLM Interpretability
Mila – Quebec AI Institute · Universit´e de Montr´eal · McGill University
PLUME: Latent Reasoning Based Universal Multimodal Embedding
Apr 2, 2026Chenwei He, Xiangzhao Hao, Tianyu Yang +6Multimodal Embedding Multimodal IR
Southeast University · Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Apr 2, 2026Xinlei Yu, Zhangquan Chen, Yongbo He +36Continuous Latent Reasoning Language Modeling
National University of Singapore · Fudan University · Tsinghua University +16
Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning
Apr 1, 2026Swapnil ParekhLLM Backdoor Attacks Continuous Latent Reasoning
Intuit
Reasoning as Energy Minimization over Structured Latent Trajectories
Mar 30, 2026David K. JohanssonLatent-Space Planning Continuous Latent Reasoning
Polished Snow Inc.
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
Mar 18, 2026Donghang Wu, Tianyu Zhang, Yuxin Li +4Speech Language Models Continuous Latent Reasoning
College of Computing and Data Science, Nanyang Technological University · Mila, Quebec Artificial Intelligence Institute, Université de Montréal
Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
Mar 16, 2026Disha Sheshanarayana, Rajat Subhra Pal, Manjira Sinha +1Efficient Language Model Reasoning Implicit Reasoning in Language Models
Manipal University Jaipur · TCS Research
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
Mar 10, 2026Peihao Wang, Shan Yang, Xijun Wang +8LLM Reasoning Language Model-Based Control
Amazon · The University of Texas at Austin · Georgia Institute of Technology +2
Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding
Mar 9, 2026Zhongxing Xu, Zhonghua Wang, Zhe Qian +10VLM Hallucination Mitigation Multimodal Large Language Models
Monash University · Georgia Tech · Northeastern University +3
SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models
Mar 6, 2026Yunlong Chu, Minglai Shao, Yuhang Liu +4Efficient Language Model Reasoning CoT Compression
School of New Media and Communication, Tianjin University, Tianjin, China · Independent Contributor, CA, USA · School of Computer Science and Engineering, Beihang University, Beijing, China
Thinking into the Future: Latent Lookahead Training for Transformers
Mar 3, 2026Lorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli +1Autoregressive Language Modeling Sequence Prediction
Apple
How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
Feb 25, 2026Yingqian Cui, Zhenwei Dai, Bing He +7Latent Reasoning Continuous Latent Reasoning
Amazon · Michigan State University
Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning
Feb 2, 2026Yadong Wang, Haodong Chen, Yu Tian +3Sparse Autoencoders Continuous Latent Reasoning
Nanjing University of Aeronautics and Astronautics · State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 311215, China · Security Capability Center
Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization
Jan 29, 2026Jiecong Wang, Hao Peng, Zhanyi Wang +2LLM Planning Efficient Language Model Reasoning
Beihang University · Didi Chuxing
Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought
Dec 25, 2025Yuyi Zhang, Boyu Tang, Tianjie Ju +2Faithfulness of Language Model Reasoning Implicit Reasoning in Language Models
Shanghai Jiao Tong University

Apr 30, 2026J/K move · Enter open · S save

Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning

Jingcheng Deng, Zihao Wei, Liang Pang, Junhong Wu+3

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences

Reinforcement Learning RL for Language Model Reasoning Group Relative Policy Optimization Continuous Latent Reasoning Latent Reasoning

Open paper AskPDF arXiv

Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods mainly focus on supervised learning, and reinforcement learning in latent space remains highly unstable. We study this problem through the lens of Group Relative Policy Optimization (GRPO), and show that directly adapting GRPO to latent reasoning is fundamentally non-trivial: latent reasoning changes both the probability density and the sampling mechanism, causing three coupled bottlenecks: absence of intrinsic latent manifolds, where unconstrained exploration pushes rollouts off the valid latent manifold; exploration-optimization misalignment, where trajectory-level rewards can induce incorrect token-level updates; and latent mixture non-closure, where jointly reinforcing multiple correct latent paths can produce an invalid averaged state. To address them, we propose Latent-GRPO, which combines invalid-sample advantage masking, one-sided noise sampling, and optimal correct-path first-token selection. Across four low-difficulty benchmarks (e.g., GSM8K-Aug) and four high-difficulty benchmarks (e.g., AIME), Latent-GRPO improves over its latent initialization by 7.86 Pass@1 points on low-difficulty tasks and surpasses explicit GRPO by 4.27 points on high-difficulty tasks while using 3--4

\times

shorter reasoning chains. It also achieves stronger pass@

k

performance under Gumbel sampling. These results establish Latent-GRPO as an effective approach for stable and efficient latent reasoning.