Metraipolis › archive › dc_6efea1e02031

arXiv 2610.31743: Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems

Source
Metraipolis archive
Original
https://arxiv.org/abs/2610.31743
License (as archived)
CC-BY-4.0
Archived
2026-10-26T18:15:50.451Z
SHA-256 of the archived text
aa8bfd83a47c9c989e6b0c14fe758234a73655b8076634a9ff654f7d0352cc2c
Stable URL of this page
https://metraipolis.com/documento/dc_6efea1e02031

How to cite

arXiv 2610.31743: Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems — Metraipolis archive, https://arxiv.org/abs/2610.31743 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_6efea1e02031 (Metraipolis archive dc_6efea1e02031, sha256 aa8bfd83a47c9c989e6b0c14fe758234a73655b8076634a9ff654f7d0352cc2c)
BibTeX
@misc{dc6efea1e02031,
  title = {arXiv 2610.31743: Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems},
  howpublished = {Metraipolis archive},
  url = {https://arxiv.org/abs/2610.31743},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_6efea1e02031; sha256 aa8bfd83a47c9c989e6b0c14fe758234a73655b8076634a9ff654f7d0352cc2c},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.31743. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM)-based multi-agent systems (MAS) rely on role-specific prompts and execution models to solve complex tasks collaboratively. However, prompt optimization typically keeps model assignments fixed, leaving differences in role requirements and their associated inference costs outside the search. We present UniMASO, a Unified framework for heterogeneous Multi-Agent System Optimization through the joint adaptation of prompts and model assignments. UniMASO evaluates candidate updates through local, downstream, and global feedback, using cost-aware Pareto search to retain useful quality-cost trade-offs. Topology-aware co-evolution then coordinates these updates according to agent roles and dependencies. Cross-level trajectory memory further supplies historical successes and failures to guide subsequent optimization. Experiments on five benchmarks and five execution topologies show that UniMASO achieves competitive task performance at substantially lower deployment cost than the strongest homogeneous configurations. Under centralized execution, it improves the average score from 69.79 to 70.40 while reducing token-weighted deployment cost by 85.2% relative to DeepSeek-V4-Pro with MASPO. These results support joint prompt-model adaptation as an effective approach to efficient multi-agent collaboration. The code is available at https://github.com/Achilles008/UniMASO_main.

Articolo: «Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems» — Cai, Mingxiu; Xian, Haoyang; Ma, Xinyu; Wang, Yutong; Song, Zhenxi et al. (2026-10-22), arXiv:2610.31743, categoria cs.MA (sistemi multi-agente).
Fonte: https://arxiv.org/abs/2610.31743
Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv.
Consultato il 2026-10-26T18:15:46Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.