Implicit Reasoning in Language Models

Follow this topic Ask about this topic

The field asks how hidden states, recurrent or looped computation, latent tokens, and memory can support multi-step inference without generating full rationales. Approaches include distilling from explicit reasoning traces, adaptively allocating test-time computation, and using mechanistic tools such as activation patching and probes; evaluations span math, symbolic and multi-hop tasks, retrieval, commonsense, and hidden constraints. These methods can reduce token use or latency and sometimes match explicit reasoning, but results depend on supervision, model, and task, while extra computation can cause shortcuts or overthinking. A central open question is whether latent states carry causally useful, generalizable reasoning—and how to verify, interpret, and secure it when visible answers or rationales may be misleading.

Latest papers

99 papers20 papers in the last four weeks, up 122% on the four weeks before. 0.1% of all new papers.

The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
Apr 7, 2026Yi Xu, Philipp Jettkant, Laura RuisImplicit Reasoning in Language Models
University of Cambridge · MIT
What is Good? Extracting and Testing Implicit Theories of Literary Quality from LLM Reasoning Traces
Apr 7, 2026Birger MoëllComputational Literary Studies LLM-as-a-Judge
Department of Linguistics and Philology, Uppsala University, Uppsala, Sweden
Are Latent Reasoning Models Easily Interpretable?
Apr 6, 2026Connor Dilgren, Sarah WiegreffeImplicit Reasoning in Language Models LLM Reasoning
Department of Computer Science, University of Maryland, College Park, MD, USA
Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not
Apr 6, 2026Sercan KarakaşImplicit Reasoning in Language Models LLM Evaluation
University of Chicago
MedicalBench: Evaluating Large Language Models Toward Improved Medical Concept Extraction
Apr 5, 2026Zhichao Yang, Gregory D. Lyng, Sanjit Singh Batra +1Clinical Information Extraction Clinical Language Model Evaluation
Optum AI
Reliable Control-Point Selection for Steering Reasoning in Large Language Models
Apr 2, 2026Haomin Zhuang, Hojun Yoo, Xiaonan Luo +2Language Model Steering Activation Steering
University of Notre Dame
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
Therefore I am. I Think
Apr 1, 2026Esakkivel Esakkiraja, Sai Rajeswar, Denis Akhiyarov +1LLM Decision-Making Implicit Reasoning in Language Models
Khoury College of Computer Sciences Northeastern University · Mila, ServiceNow Research · ServiceNow
Grading the Unspoken: Evaluating Tacit Reasoning in Quantum Field Theory and String Theory with LLMs
Apr 1, 2026Xingyang Yu, Yinghuan Zhang, Yufei Zhang +1Scientific Reasoning in Language Models LLM Evaluation
Department of physics, Virginia Tech · Independent Researcher · Department of Computer Science and Engineering, Michigan State University
The Model Says Walk: Measuring whether LLMs Condition on Hidden Constraints
Mar 30, 2026Yubo Li, Lu Zhang, Tianchong Jiang +2Constraint-Guided Reasoning in Language Models Implicit Reasoning in Language Models
Carnegie Mellon University · Independent Researcher
What can LLMs tell us about the mechanisms behind polarity illusions in humans? Experiments across model scales and training steps
Mar 29, 2026Dario PaapeComputational Psycholinguistics Implicit Reasoning in Language Models
Department of Linguistics, University of Potsdam
Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
Mar 21, 2026Bhavya Vasudeva, Puneesh Deora, Alberto Bietti +2In-Context Learning Implicit Reasoning in Language Models
University of Southern California · University of British Columbia · Flatiron Institute
LoopRPT: Reinforcement Pre-Training for Looped Language Models
Mar 20, 2026Guo Tang, Shixin Jiang, Heng Chang +7Efficient Language Model Reasoning Implicit Reasoning in Language Models
Harbin Institute of Technology, Harbin, China · Tsinghua University, Beijing, China · The Hong Kong University of Science and Technology, Guangzhou, China
Implicit Patterns in LLM-Based Binary Analysis
Mar 19, 2026Qiang Li, XiangRui Zhang, Haining WangLLMs for Cybersecurity Implicit Reasoning in Language Models
Beijing Jiaotong University China · Virginia Tech USA
CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval
Mar 18, 2026Guangzhi Wang, Yinghao Jiao, Zhi LiuGenerative Retrieval Implicit Reasoning in Language Models
CareerInternational Research Team
Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones
Mar 16, 2026Quan ChengExplainable Artificial Intelligence LLM Interpretability
Tsinghua University
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
BrainBench: Exposing the Commonsense Reasoning Gap in Large Language Models
Mar 16, 2026Yuzhe TangCommonsense Reasoning Language Model Reasoning Evaluation
Georgia Institute of Technology
PLDR-LLMs Reason At Self-Organized Criticality
Mar 12, 2026Burc GokdenLLM Reasoning Implicit Reasoning in Language Models
Fromthesky Research Labs LLC Oregon, USA
Quantifying the Necessity of Chain of Thought through Opaque Serial Depth
Mar 10, 2026Jonah Brown-Cohen, David Lindner, Rohin ShahImplicit Reasoning in Language Models CoT Reasoning
Google DeepMind
Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs
Mar 10, 2026Saugata Purkayastha, Pranav Kushare, Pragya Paramita Pal +1Moral Reasoning in Language Models Language Model Bias Evaluation
Department of Language Science and Technology, Universität des Saarlandes · TU Darmstadt, Germany.
Adaptive Loops and Memory in Transformers: Think Harder or Know More?
Mar 9, 2026Markus Frey, Behzad Shomali, Ali Hamza Bashir +3Transformer Memory-Augmented Language Models
Lamarr Institute · Fraunhofer IAIS · University of Bonn
Making Implicit Premises Explicit in Logical Understanding of Enthymemes
Mar 6, 2026Xuyao Feng, Anthony HunterNatural Language Inference Implicit Reasoning in Language Models
Department of Computer Science, University College London, United Kingdom
X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes
Mar 5, 2026Tianxi Gao, Yufan Cai, Yusi Yuan +1Structured Reasoning in Language Models Reasoning Evaluation
National University of Singapore, Singapore
Masked diffusion LLMs can use EoS tokens for hidden reasoning
Mar 5, 2026Sarah Breckner, Sebastian SchusterMasked Diffusion Models Implicit Reasoning in Language Models
Faculty of Computer Science, University of Vienna, Vienna, Austria · UniVie Doctoral School Computer Science, University of Vienna, Vienna, Austria
Understanding the Dynamics of Demonstration Conflict in In-Context Learning
Mar 3, 2026Difan Jiao, Di Wang, Lijie HuIn-Context Learning Implicit Reasoning in Language Models
University of Toronto · King Abdullah University of Science and Technology · Mohamed bin Zayed University of Artificial Intelligence
LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval
Mar 2, 2026Jiajie Jin, Yanzhao Zhang, Mingxin Li +4Dense Retrieval Information Retrieval
Gaoling School of Artificial Intelligence, Renmin University of China · Tongyi Lab, Alibaba Group
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
Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem
Feb 25, 2026Heejin JoStructured Reasoning in Language Models Prompt Engineering
Independent Researcher
Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning
Feb 24, 2026Justin Lovelace, Christian Belardi, Sofian Zalouk +3Autoregressive Language Modeling Diffusion Language Models
Department of Computer Science, Cornell University

Apr 7, 2026J/K move · Enter open · S save

The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning

Yi Xu, Philipp Jettkant, Laura Ruis

University of Cambridge · MIT

Implicit Reasoning in Language Models

Open paper AskPDF arXiv

The viability of chain-of-thought (CoT) monitoring hinges on models being unable to reason effectively in their latent representations. Yet little is known about the limits of such latent reasoning in LLMs. We test these limits by studying whether models can discover multi-step planning strategies without supervision on intermediate steps and execute them latently, within a single forward pass. Using graph path-finding tasks that precisely control the number of required latent planning steps, we uncover a striking limitation unresolved by massive scaling: tiny transformers trained from scratch discover strategies requiring up to three latent steps, fine-tuned GPT-4o and Qwen3-32B reach five, and GPT-5.4 attains seven under few-shot prompting. Although the maximum latent planning depth models can learn during training is five, the discovered strategy generalizes up to eight latent steps at test-time. This reveals a dissociation between the ability to discover a latent strategy under final-answer supervision alone and the ability to execute it once discovered. If similar limits hold more broadly, strategies requiring multiple coordinated latent planning steps may need to be explicitly taught or externalized, lending credence to CoT monitoring.