Metraipolis › archive › dc_111f88974e26

AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference — arXiv:2611.08950

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08950
License (as archived)
CC0-1.0
Archived
2026-11-09T22:33:31.283Z
SHA-256 of the archived text
b1446284db8fe2ac81c3825aea22bc2653f04827131184ca1fc142e781a3e80a
Stable URL of this page
https://metraipolis.com/documento/dc_111f88974e26

How to cite

AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference — arXiv:2611.08950 — arXiv (en), https://arxiv.org/abs/2611.08950 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_111f88974e26 (Metraipolis archive dc_111f88974e26, sha256 b1446284db8fe2ac81c3825aea22bc2653f04827131184ca1fc142e781a3e80a)
BibTeX
@misc{dc111f88974e26,
  title = {AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference — arXiv:2611.08950},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08950},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_111f88974e26; sha256 b1446284db8fe2ac81c3825aea22bc2653f04827131184ca1fc142e781a3e80a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08950. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-Agent Debate (MAD) improves reasoning on multimodal tasks, but its accuracy and token efficiency depend on how agents interact during debate. A largely overlooked design choice is which interaction modalities agents use to exchange evidence. Existing methods rely on fixed text- or graph-based interaction, which fails to convey fine-grained multimodal evidence and thus degrades accuracy while inflating token cost due to verbose descriptions. To address this, we propose Adaptive Interaction in Multi-Agent Debate (AIM), an adaptive routing framework that dynamically selects the optimal modality combination for inter-agent interaction in multimodal MAD. Beyond text and graph, AIM introduces task-dependent modality interaction, where agents exchange targeted regions of interest from the task-specific multimodal input, such as image regions, audio segments, or spatio-temporal video clips. To determine the best combination for each instance, AIM first generates a structured baseline response and extracts interpretable routing features that capture which evidence the instance requires, how confident the baseline agent is, and how much new evidence each modality would add beyond the baseline response. A lightweight router then uses these routing features to select a modality combination that avoids both under-fusion (i.e., agents miss decisive evidence) and over-fusion (i.e., redundant modalities inflate token cost) risks. Across eight benchmarks spanning three multimodal task families, \name achieves the highest accuracy. Combining modalities improves accuracy by up to 6.4\% over the best single-modality baseline, and adapting the combination per instance adds up to 4.2\% over the most accurate fixed combination of each benchmark with up to 53.4\% fewer tokens.

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/2611.08950 — 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 2026-11-09T22:30:32.047Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).