智能体
arxiv.org ·
同一游戏，不同故事：面向大语言模型智能体的极简保守策略鲁棒性基准
该 arXiv 论文提出“Same Game, Different Story”基准，衡量 LLM 智能体在保持收益不变、仅改变语言框架时动作分布的不变性。实证部分并非新模型运行，而是对 Lorè 与 Heydari 同行评审研究的二次校准：在 GPT-3.5、GPT-4、LLaMa-2 与四类社会困境博弈中，保留原研究 60 个单元中的 24 个，共 7,200 次决策；因无法获得 trial 级文件，按已发表比率重建，并将效应幅度向零衰减 30%。在此保守设定下，汇总策略鲁棒性为 0.783（95% bootstrap 区间 0.774–0.790），朋友分享框架相对商业框架使合作提升 0.307（0.297–0.316）。作者仅支持“社会关系框架可在激励固定时改变策略选择”这一较窄结论，不外推到更广的上下文或跨基准比较。
AI推荐理由 arXiv 预印本，主题是 LLM 智能体在收益不变、仅改变语言框架时的策略鲁棒性。其具体新信息在于提出“Same Game, Different Story”基准，并基于 Lorè 与 Heydari 已发表研究做二次校准：仅保留 24/60 个单元、7,200 次决策，且因缺少 trial 级数据而按已发表比率重建，并对效应做 30% 向零衰减的保守敏感性分析，得到汇总鲁棒性 0.783（95% bootstrap 区间 0.774–0.790），朋友分享框架相对商业框架使合作提升 0.307（0.297–0.316）。局限是作者明确不将其作为新模型运行，也不外推到更广的上下文或跨基准比较，因此证据强度有限。
62
正文
Computer Science > Multiagent Systems
arXiv:2607.19670 (cs)
[Submitted on 22 Jul 2026 (v1), last revised 10 Sep 2026 (this version, v2)]
Title:Same Game, Different Story: A Minimal Conservative Strategic Robustness Benchmark for Large Language Model Agents
Authors:Seyed Pouyan Mousavi Davoudi, Arshia Gharagozlou, Alireza Amiri-Margavi, Amin Gholami Davodi, Hamidreza Hasani Balyani
View a PDF of the paper titled Same Game, Different Story: A Minimal Conservative Strategic Robustness Benchmark for Large Language Model Agents, by Seyed Pouyan Mousavi Davoudi and 4 other authors
View PDF
HTML (experimental)
Abstract:Large language model agents are increasingly deployed in settings where the value of an action depends on what other agents do. This creates a strategic reliability problem: the same game may be described as a business negotiation, a friendly compromise, a diplomatic exchange, or an abstract payoff matrix, and the model may choose different actions even when the incentives are unchanged. This paper introduces \emph{Same Game, Different Story}, a benchmark for strategic robustness: invariance of model-induced action distributions under payoff-preserving language changes. The empirical analysis uses a deliberately narrow, literature-calibrated comparison from Lorè and Heydari's peer-reviewed study: business framing versus friend-sharing framing across GPT-3.5, GPT-4, and LLaMa-2 in four social-dilemma games, with 300 initializations per retained model-game-context cell. The retained design comprises 24 of the source study's 60 cells, representing 7,200 decisions. Because trial-level files were not available from the article, the analysis is presented as a secondary calibration based on reconstructed published rates, not as new model runs. As a conservative sensitivity analysis, effect magnitudes are attenuated by 30\% toward the null: action shifts are multiplied by 0.70, and non-robustness, defined as one minus the robustness score, is multiplied by 0.70. Under this attenuation, pooled strategic robustness is 0.783 with a 95\% bootstrap interval from 0.774 to 0.790, and friend-sharing framing raises cooperation by 0.307 with a 95\% bootstrap interval from 0.297 to 0.316 relative to business framing. The analysis supports the narrower claim that social-relational framing can change strategic choices even when incentives are held fixed, without extending the analysis to a broader suite of contextual or cross-benchmark comparisons.
Comments:
Subjects:
Multiagent Systems (cs.MA)
Cite as:
arXiv:2607.19670 [cs.MA]
(or
arXiv:2607.19670v2 [cs.MA] for this version)
https://doi.org/10.48550/arXiv.2607.19670
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Alireza Amiri-Margavi Mr [view email]
[v1]
Wed, 22 Jul 2026 02:18:49 UTC (18 KB)
[v2]
Thu, 10 Sep 2026 12:35:14 UTC (14 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Same Game, Different Story: A Minimal Conservative Strategic Robustness Benchmark for Large Language Model Agents, by Seyed Pouyan Mousavi Davoudi and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.MA
new
|
recent
| 2026-07
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)