# From Simulation to Enaction: Post-trained language models recognize and react to their own generations

arXiv: https://arxiv.org/abs/2605.25459 · HTML: https://mlsanity.com/paper/2605.25459/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 15 of 15)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [Taken out of context: On measuring situational awareness in LLMs](https://mlsanity.com/paper/2309.00667/) (2023)
- [Future Lens: Anticipating Subsequent Tokens from a Single Hidden State](https://mlsanity.com/paper/2311.04897/) (2023)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [Tell me about yourself: LLMs are aware of their learned behaviors](https://mlsanity.com/paper/2501.11120/) (2025)
- [Emergent Introspective Awareness in Large Language Models](https://mlsanity.com/paper/2601.01828/) (2026)
- [Emergent Response Planning in LLMs](https://mlsanity.com/paper/2502.06258/) (2025)
- [Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct](https://mlsanity.com/paper/2410.02064/) (2024)
- [Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models](https://mlsanity.com/paper/2509.26114/) (2025)

## Built on by (most cited first, 6 of 6)

- [Verbalizable Representations Form a Global Workspace in Language Models](https://mlsanity.com/paper/2607.15495/) (2026)
- [Measuring the Assistant's Harmlessness Preferences on the User Turn](https://mlsanity.com/paper/2609.23935/) (2026)
- [LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems](https://mlsanity.com/paper/2609.33495/) (2026)
- [The Assistant as a Privileged Persona: A canonical reference in cross-persona self-recognition](https://mlsanity.com/paper/2606.00545/) (2026)
- [Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference](https://mlsanity.com/paper/2610.16717/) (2026)
- [SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise](https://mlsanity.com/paper/2610.17093/) (2026)

## Abstract (arXiv)

Language models are pretrained as passive predictors with no incentive to model the consequences of their own outputs. Post-training changes this: a model producing its own responses can benefit from recognizing that it is on-policy. We present evidence that post-trained models recognize their on-policy generations, and this recognition is implicitly encoded in their output distributions. In particular, on-policy output distribution entropy is 3--4× lower than off-policy entropy, across model families and size classes. We trace part of this effect to an internal representation of input surprise, tracking the unlikeliness of the most recent input token according to the model's prior predictions, that causally modulates output entropy. One example of these phenomena can be observed in response to open-ended prompts; post-trained models (unlike pretrained models) collapse their uncertainty over the topic of their upcoming response before the first output token; violating this cached intention with a different-topic prefill results in higher output entropy. We also tested whether models can distinguish on-policy contexts from prefills via explicit verbal report. We find that they can, but that interestingly, this explicit recognition routes through a different mechanism than implicit recognition.