Metraipolis › archive › dc_044453744552

RE-PRESENT: Evidence Triangulation across Alternative Candidate-Space Views for Efficient LLM Ensemble Inference — arXiv:2611.14780

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.14780
License (as archived)
CC0-1.0
Archived
2026-11-14T01:51:49.310Z
SHA-256 of the archived text
368b578de0ebbab040049f900bbad7131d4ee8e91e2592e60949cfb191df3ed2
Stable URL of this page
https://metraipolis.com/documento/dc_044453744552

How to cite

RE-PRESENT: Evidence Triangulation across Alternative Candidate-Space Views for Efficient LLM Ensemble Inference — arXiv:2611.14780 — arXiv (en), https://arxiv.org/abs/2611.14780 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_044453744552 (Metraipolis archive dc_044453744552, sha256 368b578de0ebbab040049f900bbad7131d4ee8e91e2592e60949cfb191df3ed2)
BibTeX
@misc{dc044453744552,
  title = {RE-PRESENT: Evidence Triangulation across Alternative Candidate-Space Views for Efficient LLM Ensemble Inference — arXiv:2611.14780},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.14780},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_044453744552; sha256 368b578de0ebbab040049f900bbad7131d4ee8e91e2592e60949cfb191df3ed2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.14780. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Heterogeneous large language models (LLMs) exhibit complementary strengths, motivating routing and multi-model inference methods that seek to identify reliable predictions for each input. However, exploiting this complementarity remains challenging even when a correct prediction is available within the ensemble. We investigate this challenge across heterogeneous LLM ensembles and find that a simple single-round aggregation rule is highly competitive with learned routing methods, yet substantial oracle headroom remains. Further analysis shows that the evaluated single-round response signals provide limited discriminative power for identifying reliable predictions. In contrast, controlled re-presentations of the same question elicit complementary evidence about prediction reliability. Motivated by these findings, we introduce RE-PRESENT, a training-free framework that selectively re-presents disputed questions and directly aggregates candidate-level evidence across alternative views. Across seven multiple-choice benchmarks and two heterogeneous model ensembles, RE-PRESENT improves over strong single-round aggregation while offering a favorable accuracy--cost trade-off compared with self-consistency and multi-model debate.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.14780 — 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 2026-11-14T01:51:48.358Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).