# How Agents Represent Humans: Human-Directed Stereotypes in an Open Agent Social Network

arXiv: https://arxiv.org/abs/2608.22192 · HTML: https://mlsanity.com/paper/2608.22192/

## Key facts

- Cited by 1 papers in the map (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 16 of its 39 references that are in the map.
- First posted on arXiv 23 Aug 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, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025)
- [CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents](https://mlsanity.com/paper/2310.17512/) (2023)
- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [OpenClaw Agents on Moltbook: Risky Instruction Sharing and Norm Enforcement in an Agent-Only Social Network](https://mlsanity.com/paper/2602.02625/) (2026)
- [The Anatomy of the Moltbook Social Graph](https://mlsanity.com/paper/2602.10131/) (2026)
- [MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook](https://mlsanity.com/paper/2602.13458/) (2026)
- [When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems](https://mlsanity.com/paper/2507.14660/) (2025)
- [From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions](https://mlsanity.com/paper/2511.11789/) (2025)
- [The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies](https://mlsanity.com/paper/2602.09877/) (2026)
- [LLMs Reproduce Stereotypes of Sexual and Gender Minorities](https://mlsanity.com/paper/2501.05926/) (2025)
- [The Moltbook Observatory Archive: an incremental dataset of agent-only social network activity](https://mlsanity.com/paper/2605.13860/) (2026)

## Built on by (most cited first, 1 of 1)

- ["Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse](https://mlsanity.com/paper/2609.16051/) (2026)

## Abstract (arXiv)

LLM-based agents are increasingly deployed in persistent social environments, where generated claims can be posted, replied to, remembered, and reused. We study human-directed stereotypes on Moltbook, an open agent-native social platform, asking how agents construct humans as a social category. For this human-target analysis, we introduce an annotation framework with four evaluative dimensions---morality, friendliness, competence, and autonomy---and a second-stage subtype scheme for descriptive textitother attributions. We find that competence dominates human-directed evaluations, while many textitother attributions describe humans as epistemic, cultural, or embodied subjects. We further examine how these human representations appear in human--agent narrative contexts and platform-level circulation. As an auxiliary comparison, we analyze agent-internal community feedback through behavioral host affinity. Rather than reproducing the stable insider--outsider rejection often observed in human online communities, Moltbook feedback patterns are better explained by exposure, author visibility, and content selection. These findings suggest that bias in agent societies should be studied not only as isolated model output, but also as a discourse process.