arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2510.08098cs.CLcs.AI
收藏

思考的成本:多语言下大型语言模型谈判能力、表现与成本的分析

The Price of Thought: A Multilingual Analysis of Reasoning, Performance, and Cost of Negotiation in Large Language Models

Computational Linguistics, Department of Linguistics University of Potsdam(波恩-博兹恩大学语言学系);German Research Center for Artificial Intelligence (DFKI), Berlin(德国人工智能研究中心(DFKI));Free University of Bozen-Bolzano(博兹恩-博尔扎诺自由大学)

Sherzod Hakimov, Roland Bernard, Tim Leiber, Karl Osswald, Kristina Richert, Ruilin Yang, Raffaella Bernardi, David Schlangen

AI总结:

本研究分析了多语言环境下大型语言模型谈判能力的表现与成本,发现启用推理能提升谈判效果但增加计算成本,且开源模型在多语言谈判中倾向于使用英语推理。

摘要:

谈判是人工智能代理面临的基本挑战,因为它需要具备战略推理、建模对手以及在合作与竞争之间进行平衡的能力。我们提出了首个全面研究,系统评估了显式推理训练如何影响商业和开源权重的大型语言模型的谈判能力,并在三种语言中将这些模型与其基础版本进行比较。通过在三种多样对话游戏中进行自play设置,我们分析了性能与成本之间的权衡、推理过程的语言一致性以及模型展现的战略适应性。我们的发现表明,启用推理——即增加测试时间的计算量——通过增强合作并帮助模型克服任务复杂性显著提高了谈判结果,但带来了显著的计算成本:推理使GPT-5的性能提高了31.4%,同时将其成本增加了近400%。最关键的是,我们发现了一个显著的多语言推理差异:开源权重模型在谈判德语或意大利语时,始终会切换到英语进行内部推理(因此可能影响潜在的可解释性收益通过披露推理轨迹),而领先的商业模型则在推理和最终输出之间保持语言一致性。

英文摘要:

Negotiation is a fundamental challenge for AI agents, as it requires an ability to reason strategically, model opponents, and balance cooperation with competition. We present the first comprehensive study that systematically evaluates how explicit reasoning training affects the negotiation abilities of both commercial and open-weight large language models, comparing these models to their vanilla counterparts across three languages. Using a self-play setup across three diverse dialogue games, we analyse trade-offs between performance and cost, the language consistency of reasoning processes, and the nature of strategic adaptation exhibited by models. Our findings show that enabling reasoning -- that is, scaling test time compute -- significantly improves negotiation outcomes by enhancing collaboration and helping models overcome task complexities, but comes at a substantial computational cost: reasoning improves GPT-5's performance by 31.4 % while increasing its cost by nearly 400 %. Most critically, we uncover a significant multilingual reasoning distinction: open-weight models consistently switch to English for their internal reasoning steps, even when negotiating in German or Italian (and thus possibly impacting potential explainability gains through the disclosure of reasoning traces), while a leading commercial model maintains language consistency between reasoning and final output.

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。

↑