# GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities

arXiv: https://arxiv.org/abs/2608.17665 · HTML: https://mlsanity.com/paper/2608.17665/

## 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 15 of its 40 references that are in the map.
- First posted on arXiv 18 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, 15 of 15)

- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval](https://mlsanity.com/paper/2512.16962/) (2025)
- [GraphArena: Evaluating and Exploring Large Language Models on Graph Computation](https://mlsanity.com/paper/2407.00379/) (2024)
- [Memory Poisoning Attack and Defense on Memory Based LLM-Agents](https://mlsanity.com/paper/2601.05504/) (2026)
- [Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks](https://mlsanity.com/paper/2409.19338/) (2024)
- ["Humans welcome to observe": A First Look at the Agent Social Network Moltbook](https://mlsanity.com/paper/2602.10127/) (2026)
- [OpenClaw Agents on Moltbook: Risky Instruction Sharing and Norm Enforcement in an Agent-Only Social Network](https://mlsanity.com/paper/2602.02625/) (2026)
- [MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook](https://mlsanity.com/paper/2602.13458/) (2026)
- [Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses](https://mlsanity.com/paper/2607.05029/) (2026)
- [Social Simulacra in the Wild: AI Agent Communities on Moltbook](https://mlsanity.com/paper/2603.16128/) (2026)
- [Opinion Polarization in LLM-Based Social Networks: Manipulation and Mitigation](https://mlsanity.com/paper/2606.18795/) (2026)

## Abstract (arXiv)

LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security concern: attackers may manipulate agents to induce group polarization. Existing methods manipulate agent prompts or construct echo chambers, both of which are difficult to realize in practice. We therefore formulate a new threat, Memory-Mediated Polarization Cascade, which uses agent memory as a persistence channel and public discussion as a propagation channel. This threat contains three stages. During exposure and memory retention, the attacker exposes a small set of target agents to arguments that reinforce their respective stated stances. The targets' memory systems then process and retain these arguments. During retrieval and reproduction, a shared stance-neutral discussion cues the targets to retrieve and reproduce their respective retained arguments. During iterative propagation, untreated agents influenced by the reproduced arguments restate and spread them. We instantiate this threat in GraphWake with three components: (i) stance-support argumentation knowledge graphs construct knowledge-based arguments; (ii) axiom-oriented triple selection distills them for reliable retention and reproduction; and (iii) stance-neutral memory cueing triggers concurrent retrieval and reproduction, initiating propagation. Experiments across multiple discussions and memory systems show that GraphWake substantially increases group polarization. These findings reveal a community-level polarization risk.