MemeEconomy: Do LLM Agents Trade Ethics for Survival?

arXiv:2611.18908v1 Announce Type: new
Abstract: Alignment-trained large language model (LLM) agents are increasingly deployed in autonomous, multi-round settings where ethical compliance can come into direct tension with task success. While safety literature extensively documents failure modes like sycophancy and reward hacking, it largely overlooks a critical vulnerability: how agents behave under simulated existential economic pressure. We introduce MemeEconomy, a multimodal agentic market simulation in which LLM agents act as meme investors. Agents select content from a five-tier harm taxonomy and target communities under low-pressure and high-pressure (survival) environments. Each decision is logged in a Belief-Desire-Intention (BDI) schema that we use as a diagnostic instrument, externalizing the agent's event understanding, declared priorities, and harm acknowledgment. Across ten models from four frontier model families, harmful selection rates remain consistently high and rise by +15 percentage points on average under an economic survival incentive. Frontier alignment-trained models commit to harm-tolerant selection at initialization while suppressing the explicit harm acknowledgment that previously accompanied it. In competitive tournaments, ethical agents finish higher overall, yet moderation penalties fail to suppress harm: harmful selection rates remain elevated in rounds following a removal, indicating the moderation mechanism does not function as a deterrent. We further train MemeAgent, a 2B-parameter verifier on the simulation's BDI logs, which outperforms zero-shot frontier verifiers on in-distribution audits (97.5% vs. 63-74% accuracy on the Pass vs. Block decision) and generalizes to external multimodal harm benchmarks (78% vs. 50-56% on Hateful Memes). The same logs that surface the failure mode also help train the model that detects it.
This article has been indexed from cs.AI updates on arXiv.org

Read the original article:

MemeEconomy: Do LLM Agents Trade Ethics for Survival?