# Prompting and chain-of-thought reasoning Area: [LLM reasoning](https://mlsanity.com/lr/index.md). HTML: https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/ ## Key facts - Prompting and chain-of-thought reasoning: 1,016 papers on arXiv since 2022 (data through 14 Oct 2026). - 613 of its 1,016 mapped papers (60%) cite “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models” (2022, arXiv 2201.11903). - 339 of its 1,016 mapped papers (33%) cite “Large Language Models are Zero-Shot Reasoners” (2022, arXiv 2205.11916). - 54 new papers 17 Sep–14 Oct. ## Most cited here - [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022), cited by 613 papers here - [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022), cited by 339 papers here - [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022), cited by 338 papers here - [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022), cited by 179 papers here - [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023), cited by 149 papers here - [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023), cited by 141 papers here - [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022), cited by 118 papers here - [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023), cited by 105 papers here - [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022), cited by 87 papers here - [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022), cited by 87 papers here ## New (17 Sep–14 Oct) - [CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation](https://mlsanity.com/paper/2610.20828/) (2026-10-14) - [Chain of Thought Monitoring Can Fail Even When CoT Is Necessary](https://mlsanity.com/paper/2610.18105/) (2026-10-13) - [Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation](https://mlsanity.com/paper/2610.17607/) (2026-10-13) - [LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators](https://mlsanity.com/paper/2610.17246/) (2026-10-12) - [One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-Thought](https://mlsanity.com/paper/2610.16798/) (2026-10-12) - [Detecting Chain-of-Thought Hijacking in Backdoored Multimodal Large Reasoning Models](https://mlsanity.com/paper/2610.16598/) (2026-10-12) - [From Stages to States: Unified Iterative Reasoning for MLLMs](https://mlsanity.com/paper/2610.15620/) (2026-10-11) - [Structural Chain-of-Thought: Reasoning with Executable Computational Graphs](https://mlsanity.com/paper/2610.15107/) (2026-10-10) - [The Thinking Leakage in Reinforcement Learning for LLMs](https://mlsanity.com/paper/2610.14270/) (2026-10-09) - [Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models](https://mlsanity.com/paper/2610.12168/) (2026-10-08) - [From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers](https://mlsanity.com/paper/2610.11472/) (2026-10-08) - [Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation](https://mlsanity.com/paper/2610.10639/) (2026-10-07) - [Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language Models](https://mlsanity.com/paper/2610.10405/) (2026-10-07) - [Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation](https://mlsanity.com/paper/2610.09587/) (2026-10-07) - [SanSi: A Looped Typed Decision Model for System 1.5 Thinking](https://mlsanity.com/paper/2610.07730/) (2026-10-06) - [COMPASS: Finding Where Reasoning Lives in Language Models](https://mlsanity.com/paper/2610.07469/) (2026-10-05) - [Base Models Can Reason By Taking a Cue From Training Data](https://mlsanity.com/paper/2610.06851/) (2026-10-05) - [What Matters for Latent Reasoning with Flow Matching](https://mlsanity.com/paper/2610.06666/) (2026-10-05) - [SIFT: Robust Meta-Faithfulness Verification of Chain-of-Thought Reasoning Under Distribution Shift](https://mlsanity.com/paper/2610.04594/) (2026-10-03) - [Learning from Repaired Reasoning: Root-Cause-Guided On-Policy Distillation](https://mlsanity.com/paper/2610.03515/) (2026-10-02) - [Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability](https://mlsanity.com/paper/2610.03509/) (2026-10-02) - [On the Chain-of-Thought Monitorability of Looped Language Models](https://mlsanity.com/paper/2610.02741/) (2026-10-02) - [Learning to Revise Reasoning with Segment-wise On-Policy Distillation](https://mlsanity.com/paper/2610.02703/) (2026-10-02) - [Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data](https://mlsanity.com/paper/2610.18878/) (2026-10-01) - [Rewarding Novel Deductions: Solver-guided Process Supervision for Logical Reasoning](https://mlsanity.com/paper/2609.34660/) (2026-10-01) - [When Reasoning Helps Action: Monitoring and Steering Chain-of-Thought in Vision-Language-Action Policies](https://mlsanity.com/paper/2610.00601/) (2026-09-30) - [When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models](https://mlsanity.com/paper/2609.39846/) (2026-09-30) - [Diagnosing On-Policy Self-Distillation for Reasoning Language Models](https://mlsanity.com/paper/2609.39118/) (2026-09-30) - [Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment](https://mlsanity.com/paper/2609.38972/) (2026-09-30) - [Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting](https://mlsanity.com/paper/2609.38958/) (2026-09-30)