SOURCE-LINKED INTELLIGENCE

A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

This paper addresses navigation by composite heterogeneous robots in a decentralized system when policy reasoning and local control operate at different update levels. In a NetLogo--Python implementation, three robots share motion dynamics but use different LLM backends. Each robot independently combines a large language model (LLM) policy agent, an Upper Confidence Bound (UCB) bandit, and a Double Deep Q-Network (Double DQN) controller; no central LLM generates team actions. LLM inference is confined to round-level policy generation and refinement rather than tick-level action selection. The

Read original source ↗ Open in workspace

recordType

paper

region

Global