Dashboard
Signal #153196POSITIVE

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

100

arXiv:2608.11207v1 Announce Type: new Abstract: 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 visi...

arXiv AI Latestabout 4 hours ago
Read Full Article

Explore with AI-Powered Tools

View All Signals

Explore more AI intelligence

Want to discover more AI signals like this?

Explore Steek
Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes | Steek AI Signal | Steek