# Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes

arXiv: https://arxiv.org/abs/2608.11207 · HTML: https://mlsanity.com/paper/2608.11207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 8 of 8)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Alignment of Language Agents](https://mlsanity.com/paper/2103.14659/) (2021)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [LLMs-augmented Contextual Bandit](https://mlsanity.com/paper/2311.02268/) (2023)
- [Survey: Multi-Armed Bandits Meet Large Language Models](https://mlsanity.com/paper/2505.13355/) (2025)
- [Lessons from Contextual Bandit Learning in a Customer Support Bot](https://mlsanity.com/paper/1905.02219/) (2019)

## Abstract (arXiv)

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.