Implicit Reasoning in Language Models

Overview

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

CardsList

107 papers9 papers in the last four weeks, down 53% on the four weeks before. 0.1% of all new papers.

  1. Chain-of-Thought Hidden States Reveal Task-Solving Directions for Direct Answers

    Nov 18, 2026Houman Mehrafarin, Ioannis KonstasCoT ReasoningEfficient Language Model Reasoning

  2. An Operationalization of Opaque Serial Depth

    Nov 12, 2026Nathan Sheffield, Alek Westover, Lukas Finnveden +3Implicit Reasoning in Language ModelsLLM Interpretability

  3. Cognitive Mapping of Learning by Thinking Mechanisms in Large Language Models

    Nov 10, 2026Dong Han, Jin Zhang, Kunyue YangImplicit Reasoning in Language ModelsCognitive Modeling

  4. MicroLens: Read, Trace, and Rewire the Residual Stream with Two Lenses

    Nov 9, 2026Nika Zahedi, Fangyi Zhu, Anna WuLLM InterpretabilityLanguage Model Introspection

  5. TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens

    Nov 1, 2026Juseon Do, Sangmin Bae, Jeesu Jung +1Implicit Reasoning in Language ModelsAdaptive Reasoning in Language Models

  6. ImplicitHop: Evaluating knowledge integration across context and memory

    Oct 30, 2026Alexander Detkov, Dashiel Karish, Matthew Oleynikov +1Knowledge Retrieval in Language ModelsLanguage Model Reasoning Evaluation

  7. Implicit Reasoning in Transformers: Bridging the Compositionality Gap in GPT-2-like Models

    Oct 28, 2026Davide Venuto, Leonardo VenutoCompositional GeneralizationOOD Generalization

  8. Ask Before You Answer: A Question-Driven Evidence Reasoning Architecture (QERA) for In-Context Learning

    Oct 26, 2026Jinhu Qi, Minda Hu, Wentao Zhang +2Evidence-Grounded QAImplicit Reasoning in Language Models

  9. Curriculum Learning Teaches LLMs Long-Horizon Implicit Reasoning, Up To A Limit

    Oct 19, 2026Jimson Huang, Maxwell Nickell, Ruowang Zhang +1Long-Horizon LLM ReasoningImplicit Reasoning in Language Models

  10. The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents

    Oct 17, 2026Jinwei Hu, Youcheng Sun, Yi Dong +1Adversarial Attacks on LLMsLLM Agent Reliability

  11. Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability

    Oct 16, 2026Qingshi Wang, Huiqi TongTheory of MindImplicit Reasoning in Language Models

  12. Sep-Latent: Separator Tokens as Natural Compression Anchors for Implicit Reasoning

    Oct 16, 2026Yinlong Xu, Jianfeng Huang, Zhengdong Zhou +5Efficient Language Model ReasoningImplicit Reasoning in Language Models

  13. Reasoning Reranking with Semantic IDs as the Sole Item Representation

    Oct 16, 2026Zhenwei Tang, Jintao Liu, Di Bai +2LLM RerankingSemantic ID Recommendation

  14. ToMStories: Interpreting Theory-of-Mind in Synthetic Narratives

    Oct 15, 2026Melanie Subbiah, Chia-En Jacklyn Tsai, Kathleen McKeownTheory of MindImplicit Reasoning in Language Models

  15. INTACT: Inducing Latent Reasoning on a Frozen Backbone

    Oct 14, 2026Kutay Tire, Atula Tejaswi, Haris Vikalo +1Efficient Language Model ReasoningImplicit Reasoning in Language Models

  16. Monitoring latent reasoning in looped language models

    Oct 13, 2026Pawel Olszowiec, Paulina Tomaszewska, Maciej Żelaszczyk +2Implicit Reasoning in Language ModelsRecursive Language Models

  17. Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation

    Oct 13, 2026Yongcan Yu, Jian Liang, Lingxiao He +5CoT DistillationLanguage Model Distillation

  18. Latent Taxonomies: How Property Induction Develops in Language Model Pre-training

    Oct 11, 2026Jan Sobotka, Ekaterina Goliakova, Marcin Detyniecki +2Inductive Reasoning in Language ModelsInductive Inference

  19. The Thinking Leakage in Reinforcement Learning for LLMs

    Oct 9, 2026Wenxuan Zhu, Shuming Liu, Bang An +4RL for Language Model ReasoningRL Post-Training

  20. CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression

    Oct 5, 2026Zhaoyang Wei, Bowen Jiang, Yanchao Hao +5Efficient Language Model ReasoningLatent Visual Reasoning

  21. Base Models Can Reason By Taking a Cue From Training Data

    Oct 5, 2026Sophie L. Wang, Amil Dravid, Rulin Shao +3LLM PromptingRL for Language Model Reasoning

  22. HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

    Oct 2, 2026Donggyun Kim, Jack Lu, Chanwoo Kim +2Efficient Language Model ReasoningLLM Inference Acceleration

  23. AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models

    Oct 1, 2026Yuxiang Wang, Kunyu Feng, Yuancheng Wang +12RL for Language Model ReasoningAudio Reasoning

  24. Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard

    Sep 30, 2026Julian Schulz, Lukas Fülle, Rieke FruengelLLM SecurityImplicit Reasoning in Language Models

  25. DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis

    Sep 29, 2026Yuan Li, Hanyun Jiang, Guowei Tian +2LLM EvaluationLLM-Based Program Synthesis

  26. Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

    Sep 22, 2026Xiaoyu Luo, Tao Ren, Wenrui Yu +3LLM InterpretabilityCoT Reasoning