Metraipolis › archive › dc_88bb375e464d

Who Should Know What? Empirical Information Design for Multi-Agent LLM Economies — arXiv:2611.07667

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07667
License (as archived): CC0-1.0
Archived: 2026-11-06T14:41:42.500Z
SHA-256 of the archived text: 13242ef2532dd38451ba4e7d884fbe287e0701ef4995d3bdaf77fa02f36c1a53
Stable URL of this page: https://metraipolis.com/documento/dc_88bb375e464d

How to cite

Who Should Know What? Empirical Information Design for Multi-Agent LLM Economies — arXiv:2611.07667 — arXiv (en), https://arxiv.org/abs/2611.07667 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_88bb375e464d (Metraipolis archive dc_88bb375e464d, sha256 13242ef2532dd38451ba4e7d884fbe287e0701ef4995d3bdaf77fa02f36c1a53)

BibTeX

@misc{dc88bb375e464d,
  title = {Who Should Know What? Empirical Information Design for Multi-Agent LLM Economies — arXiv:2611.07667},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07667},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_88bb375e464d; sha256 13242ef2532dd38451ba4e7d884fbe287e0701ef4995d3bdaf77fa02f36c1a53},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07667. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.07667 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:18:42.643Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).