Metraipolis › archive › dc_b58a207c3b5a
Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes — arXiv:2608.11207
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11207
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:15:06.932Z
- SHA-256 of the archived text
0618f13068b45d52ff77c9f03de6a787fa4dd4860fc70760da866ad93efd326d- Stable URL of this page
https://metraipolis.com/documento/dc_b58a207c3b5a
How to cite
Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes — arXiv:2608.11207 — arXiv (en), https://arxiv.org/abs/2608.11207 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b58a207c3b5a (Metraipolis archive dc_b58a207c3b5a, sha256 0618f13068b45d52ff77c9f03de6a787fa4dd4860fc70760da866ad93efd326d)
BibTeX
@misc{dcb58a207c3b5a,
title = {Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes — arXiv:2608.11207},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11207},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b58a207c3b5a; sha256 0618f13068b45d52ff77c9f03de6a787fa4dd4860fc70760da866ad93efd326d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11207. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When two LLM agents with structurally opposed objectives interact across multiple turns, the absence of a shared goal function produces not competition but collapse: the visitor capitulates, the site agent stops varying its approach, and the conversation terminates without achieving either agent's stated objective. This paper asks whether a control-theoretic governance layer can substitute for that missing goal function. The Experience Orchestrator (EO) addresses this in a simulated financial services environment where a site agent guides a visitor toward advisor contact while the visitor maintains psychologically realistic resistance. EO governs the joint trajectory through three mechanisms: a Contextual Bandit (CB) that selects content arms calibrated from real-world web analytics, a PID controller that enforces behavioral consistency via dynamic schema constraints, and a POMDP belief tracker that maintains a probabilistic model of visitor intent. Across 60,000 simulations, EO achieves a +32 percentage point lift in high-intent advisor contact rate (78.1% vs. 46.1% over a naive LLM control), with CB variant selection accounting for 97% of between-factor outcome variance -- confirming that the governance policy, not environmental initial conditions, determines where trajectories end up. Persona-level analysis reveals two distinct regimes: for visitors with no natural inclination toward conversion, the governance layer is the difference between a functional system and a non-functional one; for visitors already near alignment, a naive LLM's empathetic defaults are largely sufficient. All findings are conditional on LLM-to-LLM simulation. The PID controller has not been calibrated against real human unpredictability, and validating EO on live traffic is the critical next step. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.11207 — 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 2026-10-19T05:08:46.592Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).