SOURCE-LINKED INTELLIGENCE

From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Reliable multi-turn tool use requires an agent to preserve an evolving task state and ensure that each action remains consistent with it. However, direct function-calling and ReAct-style policies learn state tracking and action generation within the same autoregressive trajectory. This coupling creates state-action competition: the pressure to produce the next call can overwrite or ignore information accumulated earlier in the interaction. Inspired by Boyd's Observe-Orient-Decide-Act cycle, we introduce OODA-Tool, a typed closed-loop policy designed to mitigate this competition by separating s

Read original source ↗ Open in workspace

recordType

paper

region

Global