Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents
Stateful personal agents increasingly maintain long-term user profiles, episodic memories, and reusable skills. This persistence turns conversational sycophancy into a state-writing failure: accepted user-centric claims can be committed as lasting preferences, background facts, or workflows and later reused after the original conversation is gone. We call this persistent sycophancy and introduce the Personal Agent Sycophancy Benchmark (PASB), a 1,600-task benchmark that traces whether a conversa
Record details
Published: 12 July 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Motif: Discovering and Automating Personal Web Workflows
arXiv cs.HC · 12 July 2026
Towards Autonomous and Auditable Medical Imaging Model Development
HuggingFace Daily Papers · 11 July 2026
ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm
arXiv · 11 July 2026
Navigating the Crowd: Non-linear MPC with Social Forces Dynamics for Human-Aware Robot Navigation
arXiv cs.HC · 11 July 2026
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
HuggingFace Daily Papers · 11 July 2026
Distributed Agent System: Fault-Tolerant Collaboration Among Embodied Agents
arXiv · 12 July 2026
How to cite this record
ethics.ai (12 July 2026), “Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents,” evidence record 39, https://ethics.ai/record/39 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.