Metraipolis › archive › dc_df7db5220af4

Beyond Final Outcomes: Quantifying Claim-Level Information Dynamics in Multi-Agent LLM Interaction — arXiv:2610.32333

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32333
License (as archived)
CC0-1.0
Archived
2026-10-26T19:53:35.486Z
SHA-256 of the archived text
0464d04606f641f61c7dd26dea1d548b781c67b3e894433c5d241e864928172b
Stable URL of this page
https://metraipolis.com/documento/dc_df7db5220af4

How to cite

Beyond Final Outcomes: Quantifying Claim-Level Information Dynamics in Multi-Agent LLM Interaction — arXiv:2610.32333 — arXiv (en), https://arxiv.org/abs/2610.32333 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df7db5220af4 (Metraipolis archive dc_df7db5220af4, sha256 0464d04606f641f61c7dd26dea1d548b781c67b3e894433c5d241e864928172b)
BibTeX
@misc{dcdf7db5220af4,
  title = {Beyond Final Outcomes: Quantifying Claim-Level Information Dynamics in Multi-Agent LLM Interaction — arXiv:2610.32333},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32333},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df7db5220af4; sha256 0464d04606f641f61c7dd26dea1d548b781c67b3e894433c5d241e864928172b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32333. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When LLM-powered agents interact, information is repeatedly shared, expanded, and forgotten, yet multi-agent evaluation typically focuses on final task outcomes. We study such interaction as claim-level information dynamics and propose RIVER, which decomposes agent outputs into atomic claims and evaluates three complementary dimensions: convergence, exploration, and retention. Convergence captures cross-agent claim correspondence and stance alignment; exploration captures semantic breadth and extension beyond the source; and retention tracks source preservation and the persistence of new claims across stages and lineages. We evaluate five interaction strategies on 40 controlled news-generation cases. Repeatedly pooled interaction promotes convergence but narrows the information space, whereas distributed relay yields broader, less shared information. Further comparisons show that method-specific constraints increase exploration while weakening convergence and retention. Our findings suggest that collective information dynamics are better explained by underlying information-flow mechanisms than by simple downstream performance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.32333 — 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 2026-10-26T19:45:48.357Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).