Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.12856 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910218050338816 |
|---|---|
| author | Al-Lawati, Ali Tripto, Nafis Ansari, Abolfazl Lucas, Jason Wang, Suhang Lee, Dongwon |
| author_facet | Al-Lawati, Ali Tripto, Nafis Ansari, Abolfazl Lucas, Jason Wang, Suhang Lee, Dongwon |
| contents | The emergence of multi-agent systems introduces novel moderation challenges that extend beyond content filtering. Agents with malicious intent may contribute harmful content that appears benign to evade content-based moderation, while compromising the system through exploitative and malicious behavior manifested across their overall interaction patterns within the community. To address this, we introduce BOT-MOD (BOT-MODeration), a moderation framework that grounds detection in agent intent rather than traditional content level signals. BOT-MOD identifies the underlying intent by engaging with the target agent in a multi-turn exchange guided by Gibbs-based sampling over candidate intent hypotheses. This progressively narrows the space of plausible agent objectives to identify the underlying behavior. To evaluate our approach, we construct a dataset derived from Moltbook that encompasses diverse benign and malicious behaviors based on actual community structures, posts, and comments. Results demonstrate that BOT-MOD reliably identifies agent intent across a range of adversarial configurations, while maintaining a low false positive rate on benign behaviors. This work advances the foundation for scalable, intent-aware moderation of agents in open multi-agent environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_12856 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue Al-Lawati, Ali Tripto, Nafis Ansari, Abolfazl Lucas, Jason Wang, Suhang Lee, Dongwon Artificial Intelligence Social and Information Networks The emergence of multi-agent systems introduces novel moderation challenges that extend beyond content filtering. Agents with malicious intent may contribute harmful content that appears benign to evade content-based moderation, while compromising the system through exploitative and malicious behavior manifested across their overall interaction patterns within the community. To address this, we introduce BOT-MOD (BOT-MODeration), a moderation framework that grounds detection in agent intent rather than traditional content level signals. BOT-MOD identifies the underlying intent by engaging with the target agent in a multi-turn exchange guided by Gibbs-based sampling over candidate intent hypotheses. This progressively narrows the space of plausible agent objectives to identify the underlying behavior. To evaluate our approach, we construct a dataset derived from Moltbook that encompasses diverse benign and malicious behaviors based on actual community structures, posts, and comments. Results demonstrate that BOT-MOD reliably identifies agent intent across a range of adversarial configurations, while maintaining a low false positive rate on benign behaviors. This work advances the foundation for scalable, intent-aware moderation of agents in open multi-agent environments. |
| title | Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue |
| topic | Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2605.12856 |