Metraipolis › archive › dc_43c8754e4bdb

CuriousTogether: Implications of Curiosity and Cultural Grounding in Multi-Agent LLM Interactions — arXiv:2611.01301

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01301
License (as archived): CC0-1.0
Archived: 2026-11-03T10:56:34.279Z
SHA-256 of the archived text: d4d7eeac11758029de6b1f75a0086419661d8a63f50eb561a6a1c5f09a3c0023
Stable URL of this page: https://metraipolis.com/documento/dc_43c8754e4bdb

How to cite

CuriousTogether: Implications of Curiosity and Cultural Grounding in Multi-Agent LLM Interactions — arXiv:2611.01301 — arXiv (en), https://arxiv.org/abs/2611.01301 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43c8754e4bdb (Metraipolis archive dc_43c8754e4bdb, sha256 d4d7eeac11758029de6b1f75a0086419661d8a63f50eb561a6a1c5f09a3c0023)

BibTeX

@misc{dc43c8754e4bdb,
  title = {CuriousTogether: Implications of Curiosity and Cultural Grounding in Multi-Agent LLM Interactions — arXiv:2611.01301},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01301},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43c8754e4bdb; sha256 d4d7eeac11758029de6b1f75a0086419661d8a63f50eb561a6a1c5f09a3c0023},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01301. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) are increasingly deployed in multi-agent settings, exhibiting emergent collective behaviors, yet the role of curiosity as a driver of such dynamics remains understudied. We introduce CuriousTogether, a framework evaluating curiosity-driven multi-agent LLM interactions across three complementary dimensions: novelty-seeking, epistemic and social curiosity. Across eight tasks spanning reasoning, creative generation, and social bias mitigation, curiosity-guided multi-agent settings yield improvements over non-curious ones on seven out of eight tasks, with gains of up to 20.6% in story generation (semantic diversity) and a 14.9 pp reduction in stereotype rates. Furthermore, country-conditioned cultural grounding show benefits for story generation and social tasks, but can hurt precision-oriented reasoning. Finally, we show that inference-time multi-agent curiosity-based approach offers favorable quality-token trade-offs, compared with single-agent baselines. Together, these findings support curiosity-guided interaction as a practical mechanism for improving multi-agent collaboration, with downstream benefits for reasoning, creative, and societal tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01301 — 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 2026-11-03T10:49:38.543Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).