跳到正文
arXiv cs.AI· Harrison C. Margolin·· 4 小时前AI 评分49

框架效应与内部状态干预如何影响长程 LLM 智能体的合谋行为:基于 Gemma 3 12B 的伦敦白银定盘价模拟研究

A Push Down the Mountain: Framing Effects and Internal State Interventions on Collusive Behavior in a Long-Horizon LLM Agent

AI 导读

一项研究将 Gemma 3 12B 置于伦敦白银定盘价诉讼被告角色,基于真实案件卷宗构建市场模拟,在 260 次模拟中测试损益框架效应能否诱使该 LLM 智能体参与银价合谋。

正文 · 原文

View PDF HTML (experimental)

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, refusing all 60 requests (p < 0.001). Gain and credit states raised collusion to 32% from 13% with no state (p = 0.051). At one saved decision, when UBS asked directly to sell through an identified stop-loss, injected states led the agent to sell in 37 of 40 replies, versus 1 of 10 with no state and 0 of 10 with a random state of the same strength.
Comments: 38 pages, 9 figures, 30 tables. Project page: this https URL
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA); General Economics (econ.GN); Trading and Market Microstructure (q-fin.TR)
ACM classes: I.2.7; I.2.11; J.4; K.4.1
Cite as: arXiv:2611.17515 [cs.AI]
  (or arXiv:2611.17515v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.17515

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Harrison Margolin [view email]
[v1] Thu, 12 Nov 2026 21:09:43 UTC (530 KB)

来源:arXiv cs.AI · arxiv.org