# Cheap, open agents make LLM pollution harder to mitigate

arXiv: https://arxiv.org/abs/2609.31054 · HTML: https://mlsanity.com/paper/2609.31054/

## 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 6 of its 25 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 6 of 6)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks](https://mlsanity.com/paper/2306.07899/) (2023)
- [The Illusion-Illusion: Vision Language Models See Illusions Where There Are None](https://mlsanity.com/paper/2412.18613/) (2024)
- [Linguistic and Embedding-Based Profiling of Texts generated by Humans and Large Language Models](https://mlsanity.com/paper/2507.13614/) (2025)
- [Detecting The Corruption Of Online Questionnaires By Artificial Intelligence](https://mlsanity.com/paper/2308.07499/) (2023)

## Abstract (arXiv)

Large Language Model (LLM) pollution occurs when synthetic responses contaminate data intended to capture human behavior. High deployment costs have so far limited the risk posed by autonomous survey agents. However, open-weight models paired with open-source agentic frameworks may have removed this barrier. We compared the performance and detectability of nine agent configurations, ranging from fully open variants to closed commercial ones. Each agent autonomously completed a survey containing multiple response types yielding various detection checks. Fully open agents ran locally without usage fees and performed competitively with commercial alternatives. Open and commercial agents failed different sets of checks, and no single check reliably detected all agents, but open-text responses discriminated best between agents and humans. These findings identify fully open agents as a distinct risk for LLM pollution and support multilayered detection strategies emphasizing open-text analysis.