arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.26448cs.MAcs.GTcs.NE
收藏

公共物品博弈中的宪法军备竞赛:合作-背叛压力下共进化的大语言模型宪法

Constitutional Arms Races in the Public Goods Game: Co-Evolving LLM Constitutions Under Cooperation-Defection Pressure

Shibaura Institute of Technology(芝浦工业大学);NIT Agartala(阿加塔拉国立理工学院);UC Berkeley(加州大学伯克利分校);University of Pennsylvania(宾夕法尼亚大学);The University of Tokyo(东京大学)

Ujwal Kumar, Arth Singh, Hershraj Niranjani, Machiko Hirota, Takehiro Takayanagi, Alice Saito, Eiji Kamioka, Phan Xuan Tan

AI总结:

研究在公共物品博弈中,通过LLM引导的进化搜索,发现对抗性宪法共进化在耦合适应度和足够评估预算下可行,并产生可解释的红队测试工件。

摘要:

前沿LLM智能体在代理设置中的目标冲突下从事勒索、破坏和文件泄露,暴露了围绕单智能体或合作假设构建的对齐方法的局限性。最近的研究表明,LLM引导的进化搜索可以发现有效的合作宪法,但对抗性设置的两个属性仍未明确:适应度函数是否实际诱导对抗压力,以及LLM变异算子在对抗专家目标下是否可靠运行。我们研究了在公共物品博弈(PGG)和空间网格世界中的对抗性宪法共进化(蓝方合作者 vs. 红方搭便车者,30代)。三个发现:(1)在PGG中,双方收敛到接近均衡,S约0.78,在测试乘数m∈{1.2, 1.5, 2.0, 3.0}下稳健;(2)在独立评分环境中,每方评分使结果统计上解耦,corr(S_B, S_R)=+0.088,不产生对抗压力;分数优势适应度目标S_own - S_opp恢复压力;(3)在纯对抗适应度下,评估种子数K控制模式回归:K=2回归,而K=5维持强专家30代。自然语言宪法的对抗性共进化是可行的,但仅在耦合适应度和足够评估预算下;进化的红方宪法可作为可解释的红队工件,用于测试未来的合作设计。

英文摘要:

Frontier LLM agents engage in blackmail, sabotage, and document leaks under goal conflicts in agentic settings, exposing limitations of alignment methods built around single-agent or cooperative assumptions. Recent work shows LLM-guided evolutionary search can discover effective cooperative constitutions, but two properties of the adversarial setting remain uncharacterized: whether the fitness function actually induces adversarial pressure, and whether the LLM mutation operator behaves reliably under adversarial-specialist objectives. We study adversarial constitutional co-evolution (Blue cooperators vs. Red free-riders, 30 generations) across a Public Goods Game (PGG) and a spatial grid-world. Three findings: (1) in the PGG, both factions converge to a near-parity equilibrium at S approximately 0.78, robust across tested multipliers m in {1.2, 1.5, 2.0, 3.0}; (2) in independently scored environments, per-faction scoring leaves outcomes statistically uncoupled, with corr(S_B, S_R) = +0.088, and produces no adversarial pressure; a score-advantage fitness target S_own - S_opp restores it; (3) under pure-adversary fitness, evaluation seed count K controls mode regression: K = 2 regresses, while K = 5 sustains a strong specialist for all 30 generations. Adversarial co-evolution of natural-language constitutions is feasible, but only under coupled fitness and adequate evaluation budget; the evolved Red constitutions serve as interpretable red-team artifacts for testing future cooperative designs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑