Search papers, labs, and topics across Lattice.
This paper introduces DQA, a novel diagnostic question-answering framework for enterprise IT support that iteratively gathers evidence to identify root causes from ambiguous user reports. DQA maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes, enabling systematic troubleshooting. Experiments on 150 anonymized IT support scenarios show that DQA achieves a 78.7% success rate, significantly outperforming a multi-turn RAG baseline (41.3%) while also reducing the average number of turns required.
Forget generic RAG: DQA slashes IT support interaction turns in half while nearly doubling success rates by explicitly modeling diagnostic state.
Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve competing hypotheses across turns. We introduce DQA, a diagnostic question-answering framework that maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents. DQA combines conversational query rewriting, retrieval aggregation, and state-conditioned response generation to support systematic troubleshooting under enterprise latency and context constraints. We evaluate DQA on 150 anonymized enterprise IT support scenarios using a replay-based protocol. Averaged over three independent runs, DQA achieves a 78.7% success rate under a trajectory-level success criterion, compared to 41.3% for a multi-turn RAG baseline, while reducing average turns from 8.4 to 3.9.
