Arbiter: Detecting Interference in LLM Agent System Prompts
System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to conventional software. We present Arbiter, a framework combining formal evaluation rules with multi-model LLM scouring to detect interference patterns in system prompts. Applied to three major coding agent system prompts: Claude Code (Anthropic), Codex CLI (OpenAI), and Gemini CLI (Google), we identify 152 findings across the undirected scouring phase and 2
Record details
Published: 9 March 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.
When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Markets
arXiv cs.AI · 22 July 2026
When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Markets
arXiv cs.CY · 23 July 2026
Microsoft joins Google in backing Go for AI agents — OpenAI and Anthropic lag
The New Stack AI · 11 July 2026
An opinionated guide to which AI to use to do stuff
Simon Willisons Weblog · 27 July 2026
Enigma raises $71M to develop foundation models for robots
SiliconANGLE AI · 27 July 2026
Gemini 3.7 Flash lands with coding gains and undercuts its three-week-old predecessor's price by 50%
The Decoder · 13 August 2026
How to cite this record
ethics.ai (9 March 2026), “Arbiter: Detecting Interference in LLM Agent System Prompts,” evidence record 7462, https://ethics.ai/record/7462 (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.