arXiv cs.AI· Mete Erdogan, Mirac Suzgun, Aneesh Pappu, Guowei Xu, Batu El, Andrew A. Schoen, Furong Huang, John P. Dickerson, Mert Pilanci, James Zou·· 11 小时前AI 评分34
多智能体 LLM 经济中的信息设计：披露越细未必越好
Who Should Know What? Empirical Information Design for Multi-Agent LLM Economies
AI 导读
研究者提出“经验信息设计”框架，在固定交互规则与模型的前提下，系统比较不同信息披露策略对 LLM 智能体市场表现的影响。
正文 · 原文
Abstract:The performance of multi-agent LLM systems depends not only on the capabilities of the underlying models but also on information-sharing policies, which govern what information each agent observes and at what level of detail. But does providing AI agents with more detailed information always improve collective outcomes, or can transparency paradoxically degrade efficiency? To investigate this, we introduce empirical information design, an experimental framework that systematically compares disclosure policies across economic markets populated by LLM agents, while holding interaction rules and models fixed. We evaluate ten frontier LLMs in multi-resource trade, bilateral bargaining, and double auctions, using ground-truth utilities to decouple identified opportunities from realized outcomes. We find that finer information disclosure yields highly model-dependent results. In trade, revealing exact valuations rather than ordinal preference rankings reduces realized gains for GPT-6 Sol (from 98% to 91% of maximum) yet increases them for Claude Sonnet 5 (from 72% to 86%). In bargaining, exact information leads Grok 4.7 to produce less balanced agreements, whereas Claude Opus 5.5 divides gains symmetrically. In double auctions, full disclosure inflates price demands, triggering market breakdown and lowering welfare for Gemini 3.1 Pro (97% to 78%), Claude Opus 5.5 (94% to 64%), and Grok 4.7 (97% to 62%). Overall, these results suggest that model selection and information design must be co-optimized, as LLMs vary in how their strategic responses to information impact system objectives.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07667 [cs.AI] |
| (or arXiv:2611.07667v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07667 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mete Erdogan [view email]
[v1]
Thu, 5 Nov 2026 08:51:37 UTC (648 KB)
来源：arXiv cs.AI · arxiv.org