Metraipolis › archive › dc_ebfb79909280

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

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.31743
License (as archived): CC0-1.0
Archived: 2026-10-26T11:16:30.533Z
SHA-256 of the archived text: f19d42b825e29ef3111eed2ca338ad556140e5e1f22a72aa40f6c1b4c870c22a
Stable URL of this page: https://metraipolis.com/documento/dc_ebfb79909280

How to cite

Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems — arXiv:2610.31743 — arXiv (en), https://arxiv.org/abs/2610.31743 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebfb79909280 (Metraipolis archive dc_ebfb79909280, sha256 f19d42b825e29ef3111eed2ca338ad556140e5e1f22a72aa40f6c1b4c870c22a)

BibTeX

@misc{dcebfb79909280,
  title = {Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems — arXiv:2610.31743},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31743},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebfb79909280; sha256 f19d42b825e29ef3111eed2ca338ad556140e5e1f22a72aa40f6c1b4c870c22a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), 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 this https URL .

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/2610.31743 — 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 2026-10-26T11:16:29.815Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).