Skip to content
conftrace_
2026 EMNLP EMNLP 2026

TRACE: Traceable Root-cause Analysis with Calibrated Evidence-grounded agents

AbstractRoot Cause Analysis (RCA) for defects in large e-commerce enterprises is manual and slow: a single defect spanning thousands of microservices and SOPs takes experts one to two weeks to diagnose. Generic agentic RCA frameworks fail on this workload because they stop at proximate causes, cannot verify numeric claims, ignore past reviewer decisions, and return enumerated hypotheses rather than the quantified narratives business teams act on. We present Trace, an end-to-end agentic RCA system that combines supervised hypothesis-driven investigation with recursive why-drilling, an evidence-traceable multi-tool suite with stable artifact identifiers, a feedback retrieval and ingestion pipeline, and a two-layer confidence framework combining six mechanistic checks with an LLM judge - including a novel numerical-traceability score. Across several thousand cohorts spanning eight use cases in three metric categories (cost, quality, and inventory), Trace achieves 65.4% expert acceptance; on a 240-cohort head-to-head benchmark it reaches 67.1% vs. 38.8% for a matched ReAct baseline (+28.3pp, p<0.001) with calibrated confidence (AUC 0.819, ECE 0.041).

More from EMNLP 2026

All EMNLP 2026 papers →