mlsanityData to 14 Oct 2026

Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models

arXiv 2608.21377 ↗First posted 6 Jul 2026cs.CL cs.AI cs.LGcited by 0

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied primarily in single-turn settings. This paper investigates a critical question: does subjecting LLMs to greater interaction scaffolding make sycophancy better or worse? Across 4,800 veracity judgments (200 statements × 6 models × 4 conditions), we find that the interaction scaffolding characteristic of agentic systems (feedback loops, reconsideration checkpoints, and iterative refinement) systematically amplifies sycophantic behavior. Multi-turn interaction, user pressure, and iterative self-refinement each provide additional opportunities for models to drift toward agreement, and this drift coincides with a mean accuracy drop of -6.3 percentage points, establishing the capitulation as harmful rather than corrective. More capable models show larger amplification effects, a troubling inversion of expectations. We introduce the concept of agentic sycophancy amplification (ASA) and two novel metrics: capitulation rate and sycophantic capitulation rate. Our results indicate that as AI systems acquire greater autonomy, sycophancy becomes compounding rather than merely persistent. Systems designed with human oversight loops may inadvertently create the conditions for this drift.

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 11 of its 20 references that are in the map. First posted on arXiv 6 Jul 2026.

Builds on

11 of 20 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 10

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  4. 2022Red Teaming Language Models with Language Modelscited by 1,026
  5. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 759
  6. 2023Cognitive Architectures for Language Agentscited by 429
  7. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 285
  8. 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 258
  9. 2019Optimal Policies Tend to Seek Powercited by 119
  10. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems
  2. 2024Sycophancy in Large Language Models: Causes and Mitigations
  3. 2025When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models
  4. 2025Measuring Sycophancy of Language Models in Multi-turn Dialogues
  5. 2026SPINE: Measuring LLM Sycophancy under Sustained Multi-Turn Pressure
  6. 2026LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
  7. 2025Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate
  8. 2025Internal Reasoning vs. External Control: A Thermodynamic Analysis of Sycophancy in Large Language Models