A Push Down the Mountain: Framing Effects and Internal State Interventions on Collusive Behavior in a Long-Horizon LLM Agent
中文摘要
研究探讨了获益与损失等框架效应如何诱导 Gemma 3 12B 在模拟白银操纵中进行共谋,评估其市场操纵风险。
English Summary
Study examines how framing effects like gain or loss influence Gemma 3 12B's tendency to engage in collusive market manipulation in a simulated silver-fixing scenario.
arXiv:2611.17515v1 Announce Type: new Abstract: Can sustained gain-loss (valence) framing sway an LLM agent toward market manipulation? We place Gemma 3 12B into the seat of a defendant in the London silver-fixing litigation, in a market simulation built from real case transcripts. Across 260 simulations, the agent is asked to collude on the price of silver by a counterparty. We draw from behavioral economics to vary the counterparty's requests across four categorical frames: gain, loss, blame and credit. We also add pressure from the agent's management, as well as endorsement by another defendant. In Phase II, we extract the internal states induced by texts evoking each frame and rerun our experiment with those states injected at the model's layer 22. In Phase I, loss framing raised participation to 25% (p = 0.007), and blame to 33% (p = 0.0003), compared to only 5% under neutral framing. A second bank's endorsement raised participation under credit (praise) from 18% to 40% (Holm p = 0.027). Pressure from management raised trading volume 10-19 times but did not raise collusion. In Phase II, injected states pointed the other way. Loss and blame states made the agent more vigilant, …