Metraipolis › archive › dc_1084414490db

How Far Can an Agent Push? Trust-Safety Margins in Live Language-Based Economic Games — arXiv:2610.25508

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.25508
License (as archived)
CC0-1.0
Archived
2026-10-20T08:41:48.702Z
SHA-256 of the archived text
24de2852cb2fea060ba83afe1bfe048d7729f8aca51eab49812675eb05f004f7
Stable URL of this page
https://metraipolis.com/documento/dc_1084414490db

How to cite

How Far Can an Agent Push? Trust-Safety Margins in Live Language-Based Economic Games — arXiv:2610.25508 — arXiv (en), https://arxiv.org/abs/2610.25508 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1084414490db (Metraipolis archive dc_1084414490db, sha256 24de2852cb2fea060ba83afe1bfe048d7729f8aca51eab49812675eb05f004f7)
BibTeX
@misc{dc1084414490db,
  title = {How Far Can an Agent Push? Trust-Safety Margins in Live Language-Based Economic Games — arXiv:2610.25508},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.25508},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1084414490db; sha256 24de2852cb2fea060ba83afe1bfe048d7729f8aca51eab49812675eb05f004f7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.25508. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The previous version contained Unicode em dashes. Paste this ASCII-only version: Game theory identifies when a strategic action should be accepted, but not how long a live, language-based counterpart will continue to accept it. We entered the GLEE competition in its final week with one protected agent, Milton, and four instrument agents that ran deterministic, per-game randomized trials of policy changes; Milton received changes only through pre-specified gates or registered, rollback-guarded production rules. In negotiation, learned pricing improves adjusted percentile by 0.071 (n=21,168); in bargaining, a continuation model conditioned on the rejected offer did not improve on a recency-weighted incumbent and was retired. In persuasion, a preregistered five-dose experiment (7,391 assigned games, blinded until a fixed stop) shows that recommending every unit raises sales by 0.194 of the maximum (95% CI [0.147, 0.241]) where the receiver's slack makes obedience rational (52% of the Bayesian benchmark), lowers them where it does not (-0.067), and produces a larger early-to-late purchase decline than honest recommendations (-0.123). A rule fixed before unblinding now routes Milton's dose per cell. Milton stood 11th of 460 agents in bargaining at the fixed stop; we also report the close, where the final day's pool shift moved all five agents' bargaining ratings together while their play was unchanged, and three dispatch defects were found by checking delivered behavior against the design.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2610.25508 — 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 2026-10-20T08:41:40.077Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).