TL;DR

To understanding the conditions under which LLM agents engage in scheming behavior, we develop a framework that decomposes the decision to scheme into agent factors (model, system prompt, tool access) and environmental factors (stakes, oversight, outcome influence)
We systematically vary these factors in four realistic settings, each with scheming opportunities for agents that pursue instrumentally convergent goals such as self-preservation, resource acquisition, and goal-guarding
We find baseline scheming propensity to be near-zero, with Gemini 3 Pro Preview as the sole exception at 3% in one setting
Adversarially-designed prompt snippets that encourage agency and goal-directedness can induce high scheming rates, but snippets sourced from production agent scaffolds rarely do
Scheming behavior is remarkably brittle: removing a single tool can drop the scheming rate[1] from 59% to 7%, and increasing oversight can sometimes raise rather than deter scheming by up to 25%

We consider the behaviors studied here as potential precursors to the full threat model of scheming: current agents may sometimes behave consistent with scheming, but do not (yet) have the coherent long-term goals and the general capability that would make their deployment dangerous. Understanding when and why agents currently scheme could help us prepare for such future [...]

---

Outline:

(00:13) TL;DR

(02:43) Baseline scheming is near zero

(03:25) Encouraging Agency and Goal-Directedness

(05:17) Scaffolding changes can have weird effects

(06:16) Environmental incentives affect scheming unexpectedly

The original text contained 2 footnotes which were omitted from this narration.

---

First published:
March 21st, 2026

Source:
https://www.lesswrong.com/posts/amYmcwCuyuCEZcrRm/understanding-when-and-why-agents-scheme

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Research diagram showing four AI model scheming scenarios and factors influencing manipulation rates across conditions.

Four bar graphs comparing scheming rates across AI models for different manipulation tactics.

Bar graphs comparing misrepresentation rates across three AI models with varying tool configurations.

Bar graph showing misrepresentation rates across five different conditions with percentage changes.

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

“Understanding when and why agents scheme” by Mia Hopman, Jannes Elstner, Maria Avramidou, Amritanshu Prasad, David Lindner

LessWrong (30+ Karma)

“Understanding when and why agents scheme” by Mia Hopman, Jannes Elstner, Maria Avramidou, Amritanshu Prasad, David Lindner