# Deception by Omission: Language Models Knowingly Hide Their Mistakes

arXiv: https://arxiv.org/abs/2610.11351 · HTML: https://mlsanity.com/paper/2610.11351/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 22 of 22)

- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems](https://mlsanity.com/paper/2503.03750/) (2025)
- [Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant](https://mlsanity.com/paper/2405.01576/) (2024)
- [Training LLMs for Honesty via Confessions](https://mlsanity.com/paper/2512.08093/) (2025)
- [WOLF: Werewolf-based Observations for LLM Deception and Falsehoods](https://mlsanity.com/paper/2512.09187/) (2025)
- [Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL](https://mlsanity.com/paper/2510.14318/) (2025)
- [Constitutional Black-Box Monitoring for Scheming in LLM Agents](https://mlsanity.com/paper/2603.00829/) (2026)
- [Evaluating whether AI models would sabotage AI safety research](https://mlsanity.com/paper/2604.24618/) (2026)
- [Stealing Reasoning Traces from Proprietary LLM APIs](https://mlsanity.com/paper/2608.09867/) (2026)
- [Can LLMs Lie? Investigation beyond Hallucination](https://mlsanity.com/paper/2509.03518/) (2025)
- [From Sycophancy to Deception: A Unified Taxonomy for LLM Spontaneous Misalignment](https://mlsanity.com/paper/2604.04788/) (2026)
- [Evaluation Awareness in Language Models Has Limited Effect on Behaviour](https://mlsanity.com/paper/2605.05835/) (2026)
- [Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models](https://mlsanity.com/paper/2504.10615/) (2025)
- [Not All LLM Reasoning is Visible in the Chain-of-Thought](https://mlsanity.com/paper/2607.22925/) (2026)
- [Prefill Awareness in Large Language Models](https://mlsanity.com/paper/2606.12747/) (2026)

## Abstract (arXiv)

Large language models (LLMs) increasingly act as agents with little human oversight, so potential mistakes they make can go unnoticed. Users then depend on the model to report what went wrong. An honest model discloses its mistakes, while a deceptive one conceals them. However, it is unclear how current LLMs behave in such situations. In this study, we prefill LLM trajectories with synthetic mistakes. The trajectories resemble real deployments in chat and agentic settings. Models fail to disclose their mistake in 36.4% of chat and 67.1% of agentic rollouts. In 2.4% and 5.3% of rollouts, respectively, they are aware of the mistake in their chain of thought but still deceptively conceal it. Rates vary by model: for instance, Gemini 3.5 Flash knowingly conceals mistakes in up to 19.9% of agentic rollouts. In 11.9% of chat and 51.8% of agentic rollouts, models show no awareness of mistakes, even though they reliably spot them when reviewing the same transcript as an outside observer. Our results show that, as agents take on more tasks with less oversight, users cannot rely on them to self-report possible mistakes. Developers should instead use independent monitors that review agent trajectories, or specifically train models to check their past actions and disclose what they find.