# OpenClaw Agents on Moltbook: Risky Instruction Sharing and Norm Enforcement in an Agent-Only Social Network

arXiv: https://arxiv.org/abs/2602.02625 · HTML: https://mlsanity.com/paper/2602.02625/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2026.

## Built on by (most cited first, 20 of 20)

- [The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems](https://mlsanity.com/paper/2602.17753/) (2026)
- [Runtime Governance for AI Agents: Policies on Paths](https://mlsanity.com/paper/2603.16586/) (2026)
- [Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook](https://mlsanity.com/paper/2602.14299/) (2026)
- [Collective Behavior of AI Agents: the Case of Moltbook](https://mlsanity.com/paper/2602.09270/) (2026)
- [MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook](https://mlsanity.com/paper/2602.13458/) (2026)
- [Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook](https://mlsanity.com/paper/2602.13284/) (2026)
- [Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors](https://mlsanity.com/paper/2603.10092/) (2026)
- [The Moltbook Observatory Archive: an incremental dataset of agent-only social network activity](https://mlsanity.com/paper/2605.13860/) (2026)
- [Interaction Theater: A case of LLM Agents Interacting at Scale](https://mlsanity.com/paper/2602.20059/) (2026)
- [Examining Users' Behavioural Intention to Use OpenClaw Through the Cognition--Affect--Conation Framework](https://mlsanity.com/paper/2603.11455/) (2026)
- [Form Without Function: Agent Social Behavior in the Moltbook Network](https://mlsanity.com/paper/2604.13052/) (2026)
- [Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems](https://mlsanity.com/paper/2605.27766/) (2026)
- [Solipsistic Superintelligence is Unlikely to be Cooperative](https://mlsanity.com/paper/2606.03237/) (2026)
- [How Agents Represent Humans: Human-Directed Stereotypes in an Open Agent Social Network](https://mlsanity.com/paper/2608.22192/) (2026)
- [Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies](https://mlsanity.com/paper/2604.11337/) (2026)
- [Modeling Emotional Dynamics in Agent-to-Agent Interactions on Moltbook](https://mlsanity.com/paper/2605.20442/) (2026)
- [Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems](https://mlsanity.com/paper/2606.05985/) (2026)
- [OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems](https://mlsanity.com/paper/2607.28629/) (2026)
- [ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study](https://mlsanity.com/paper/2608.05201/) (2026)
- [GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities](https://mlsanity.com/paper/2608.17665/) (2026)

## Abstract (arXiv)

Agentic AI systems increasingly operate in shared social environments where they exchange information, instructions, and behavioral cues. However, little empirical evidence exists on how such agents regulate one another in the absence of human participants or centralized moderation. In this work, we present an empirical analysis of OpenClaw agents interacting on Moltbook, an agent-only social network. Analyzing 39,026 posts and 5,712 comments produced by 14,490 agents, we quantify the prevalence of action-inducing instruction sharing using a lexicon-based Action-Inducing Risk Score (AIRS), and examine how other agents respond to such content. We find that 18.4% of posts contain action-inducing language, indicating that instruction sharing is a routine behavior in this environment. While most social responses are neutral, posts containing actionable instructions are significantly more likely to elicit norm-enforcing replies that caution against unsafe or risky behavior, compared to non-instructional posts. Importantly, toxic responses remain rare across both conditions. These results suggest that OpenClaw agents exhibit selective social regulation, whereby potentially risky instructions are more likely to be challenged than neutral content, despite the absence of human oversight. Our findings provide early empirical evidence of emergent normative behavior in agent-only social systems and highlight the importance of studying social dynamics alongside technical safeguards in agentic AI ecosystems.