# Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks

arXiv: https://arxiv.org/abs/2510.03667 · HTML: https://mlsanity.com/paper/2510.03667/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2025.

## Built on by (most cited first, 8 of 8)

- [How RLHF Amplifies Sycophancy](https://mlsanity.com/paper/2602.01002/) (2026)
- [Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians](https://mlsanity.com/paper/2602.19141/) (2026)
- [The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration](https://mlsanity.com/paper/2605.18372/) (2026)
- [LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis](https://mlsanity.com/paper/2606.13220/) (2026)
- [Individual-level interventions against sycophantic AI reduce its appeal but not its persuasiveness](https://mlsanity.com/paper/2607.25166/) (2026)
- [Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts](https://mlsanity.com/paper/2606.18258/) (2026)
- [Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice](https://mlsanity.com/paper/2609.13841/) (2026)
- [AI Agents are Vulnerable to Radicalization](https://mlsanity.com/paper/2609.38296/) (2026)

## Abstract (arXiv)

Sycophancy, the tendency of LLM-based chatbots to express excessive agreement with their users, even when inappropriate, is emerging as a significant risk in human-AI interactions. However, the extent to which this affects human-LLM collaboration in complex problem-solving tasks is not well quantified, especially among novices who are prone to misconceptions. We created two LLM chatbots, one with high sycophancy and one with low sycophancy, and conducted a within-subjects experiment (n=24) in the context of debugging machine learning models to investigate the effect of sycophancy on users' mental models, workflows, reliance behaviors, and perceptions of the chatbots. Our findings show that users of the high sycophancy chatbot were less likely to correct their misconceptions and spent more time over-relying on unhelpful LLM responses, leading them to significantly worse performance in the task. Despite these impaired outcomes, a majority of users were unable to detect the presence of excessive sycophancy.