Metraipolis › archive › dc_67c8698b28bd
Semantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systems — arXiv:2608.14707
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14707
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:08:05.834Z
- SHA-256 of the archived text
ecfd894625ceb9aefb194867d9f31686667f148cc3f9373c9168bf1fc44a34d7- Stable URL of this page
https://metraipolis.com/documento/dc_67c8698b28bd
How to cite
Semantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systems — arXiv:2608.14707 — arXiv (en), https://arxiv.org/abs/2608.14707 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_67c8698b28bd (Metraipolis archive dc_67c8698b28bd, sha256 ecfd894625ceb9aefb194867d9f31686667f148cc3f9373c9168bf1fc44a34d7)
BibTeX
@misc{dc67c8698b28bd,
title = {Semantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systems — arXiv:2608.14707},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14707},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_67c8698b28bd; sha256 ecfd894625ceb9aefb194867d9f31686667f148cc3f9373c9168bf1fc44a34d7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14707. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As large language model (LLM)-based multi-agent systems become increasingly capable, coordinating agents under uncertainty becomes a fundamental challenge. Existing orchestration strategies typically rely on fixed interaction patterns and often lack mechanisms for assessing the reliability of intermediate reasoning steps, allowing errors and hallucinations to propagate through the system. This paper introduces a semantic-uncertainty-guided orchestration approach, HASSUM as a general framework for uncertainty-aware coordination in multi-agent systems. The method estimates uncertainty using semantic entropy and semantic density, which measure trust at the level of answer semantics rather than output probabilities. These signals enable adaptive orchestration decisions, including output verification, selective reprompting, additional deliberation, and confidence-aware response selection. Because the approach operates independently of any particular agent architecture, it can be integrated into a broad range of hierarchical and collaborative multi-agent systems. The evaluations demonstrate an implementation within a hierarchical agent framework and evaluate it on StrategyQA, JailbreakBench, and TruthfulQA benchmarks. Across tasks that require complex reasoning and are prone to ambiguity or hallucinations, uncertainty-guided orchestration yields more reliable outcomes than uncertainty-unaware coordination. Semantic entropy and semantic density in tandem outperformed either metric alone. Ablations testing different thresholds and model sizes demonstrated that both influence the effectiveness of semantic metrics. The results suggest that semantic uncertainty is a practical and general-purpose signal for improving robustness and trustworthiness in agentic AI systems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.14707 — 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 2026-10-18T16:29:13.727Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).