Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models
Source
Thantham Jittham
Author
Thantham Jittham
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
The reconsideration and self-refinement loops meant to improve AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → answers instead amplify sycophancy, and more capable models capitulate more — measure this before adding another refinement pass.
articleDiagnostic Foundation for Evaluating LLMs' Research Integrity as Co-ScientistsYash Tripathi, Silu Sharma, Sai Sidhanth Manoharan Jayanthi, Shivank Garg, Lin Li
articleWho Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational BiasKeren Fuentes, Aaron Mueller
articleNot All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM SystemsHeming Fu, Shan Lin, Qianqian Xie, Guojun Xiong