# Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

arXiv: https://arxiv.org/abs/2504.09762 · HTML: https://mlsanity.com/paper/2504.09762/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 36 of its 90 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 30 of 36)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Let's Think Dot by Dot: Hidden Computation in Transformer Language Models](https://mlsanity.com/paper/2404.15758/) (2024)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model](https://mlsanity.com/paper/2503.05132/) (2025)
- [MiniLLM: On-Policy Distillation of Large Language Models](https://mlsanity.com/paper/2306.08543/) (2023)
- [LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!](https://mlsanity.com/paper/2502.07374/) (2025)
- [Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2402.13950/) (2024)
- [DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning](https://mlsanity.com/paper/2504.07128/) (2025)
- [Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping](https://mlsanity.com/paper/2402.14083/) (2024)
- [On Designing Effective RL Reward at Training Time for LLM Reasoning](https://mlsanity.com/paper/2410.15115/) (2024)
- [Concise Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2504.05185/) (2025)
- [Best-of-N Jailbreaking](https://mlsanity.com/paper/2412.03556/) (2024)
- [The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities](https://mlsanity.com/paper/2408.13296/) (2024)
- [Understanding Aha Moments: from External Observations to Internal Mechanisms](https://mlsanity.com/paper/2504.02956/) (2025)

## Built on by (most cited first, 30 of 37)

- [Trace Length is a Simple Uncertainty Signal in Reasoning Models](https://mlsanity.com/paper/2510.10409/) (2025)
- [Code Like Humans: A Multi-Agent Solution for Medical Coding](https://mlsanity.com/paper/2509.05378/) (2025)
- [Lexical Hints of Accuracy in LLM Reasoning Chains](https://mlsanity.com/paper/2508.15842/) (2025)
- [Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation](https://mlsanity.com/paper/2505.13792/) (2025)
- [The Need for Verification in AI-Driven Scientific Discovery](https://mlsanity.com/paper/2509.01398/) (2025)
- [Probing the Trajectories of Reasoning Traces in Large Language Models](https://mlsanity.com/paper/2601.23163/) (2026)
- [Humans Perceive Wrong Narratives from AI Reasoning Texts](https://mlsanity.com/paper/2508.16599/) (2025)
- [State over Tokens: Characterizing the Role of Reasoning Tokens](https://mlsanity.com/paper/2512.12777/) (2025)
- [Do explanations generalize across large reasoning models?](https://mlsanity.com/paper/2601.11517/) (2026)
- [Aletheia: What Makes RLVR For Code Verifiers Tick?](https://mlsanity.com/paper/2601.12186/) (2026)
- [Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics](https://mlsanity.com/paper/2605.18549/) (2026)
- [Beyond Consensus: Trace-Level Synthesis in Mixture of Agents](https://mlsanity.com/paper/2605.29116/) (2026)
- [Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following](https://mlsanity.com/paper/2505.02763/) (2025)
- [Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding](https://mlsanity.com/paper/2507.11198/) (2025)
- [The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?](https://mlsanity.com/paper/2604.06192/) (2026)
- [Retrieval-augmented reasoning with lean language models](https://mlsanity.com/paper/2508.11386/) (2025)
- [On the Notion that Language Models Reason](https://mlsanity.com/paper/2511.11810/) (2025)
- [The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics](https://mlsanity.com/paper/2602.14903/) (2026)
- [Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning](https://mlsanity.com/paper/2603.13988/) (2026)
- [CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation](https://mlsanity.com/paper/2604.09746/) (2026)
- [Feedback-Induced Performance Decline in LLM-Based Decision-Making](https://mlsanity.com/paper/2507.14906/) (2025)
- [Illusions of reflection: open-ended task reveals systematic failures in Large Language Models' reflective reasoning](https://mlsanity.com/paper/2510.18254/) (2025)
- [Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)](https://mlsanity.com/paper/2602.06266/) (2026)
- [Humans and LLMs Diverge on Probabilistic Inferences](https://mlsanity.com/paper/2602.23546/) (2026)
- [Tracing Uncertainty in Language Model "Reasoning"](https://mlsanity.com/paper/2605.07776/) (2026)
- [What Am I Missing? Question-Answering as Hidden State Probing](https://mlsanity.com/paper/2605.31561/) (2026)
- [Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction](https://mlsanity.com/paper/2510.25426/) (2025)
- [Disagreement as Data: Reasoning Trace Analytics in Multi-Agent Systems](https://mlsanity.com/paper/2601.12618/) (2026)
- [LLM Reasoning Is Latent, Not the Chain of Thought](https://mlsanity.com/paper/2604.15726/) (2026)
- [What properties of reasoning supervision are associated with improved downstream model quality?](https://mlsanity.com/paper/2605.13290/) (2026)

## Abstract (arXiv)

Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called sayreasoning traces or even saythinking traces -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.