Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue (2510.08175v1)

Abstract: The latency-quality tradeoff is a fundamental constraint in open-domain dialogue AI systems, since comprehensive knowledge access necessitates prohibitive response delays. Contemporary approaches offer two inadequate solutions: lightweight instruct models achieve sub-second latency but lack reasoning depth, while tool-augmented ReAct agents enhance factuality through external knowledge at the cost of synchronous execution that blocks interaction during re- trieval processes. PMFR is thus proposed, with a tempo- ral decoupling framework that fundamentally resolves the contradiction through asynchronous knowledge orchestra- tion. PMFR employs three coordinated components: (1) a Knowledge Adequacy Evaluator for real-time sufficiency assessment, (2) a Lightweight Response Generator for imme- diate user interaction, and (3) an Asynchronous Knowledge Refinement Agent for background knowledge enhancement. This architecture maintains continuous conversational flow while progressively enriching knowledge coverage through intelligent triggering mechanisms. Evaluation results on Top- iOCQA demonstrate PMFR outperforms brute-force scaling: PMFR achieves 95.3% latency reduction (23.38s -> 1.09s) while preserving response quality comparable to heavyweight synchronous baselines (GEval-C: 0.613 vs. 0.620).