5 papers · 1 filter
Lightweight, Rubric-Guided Trajectory Evaluation for Production AI Agents
Linh-An Phan, MingXue Wang, Guangyu Wu +3
Trajectory evaluation is essential for improving the reliability of LLM-based agents, but production use makes it expensive to run repeatedly. Modern agents generate long traces co…
The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions
Filip Klubicka, Vasudevan Nedumpozhimana, Sneha Rautmare +3
In the age of large language models, Natural Language to SQL (NL2SQL) translation remains an open problem with many useful applications. We explore interactions between several NL2…
Log-Insight: Automating Microservice Incident Diagnosis via Neuro-Symbolic Log Analysis
Carlos Garcia-Hernandez, Aymane Abdali, Guangyu Wu +4
Diagnosing production incidents in large-scale microservice systems is time-critical for Site Reliability Engineers (SREs). A single 30-minute incident window in our deployment can…
Efficient Multi-Cohort Inference for Long-Term Effects and Lifetime Value in A/B Testing with User Learning
Dario Simionato, Andrea Tonon, Mingxue Wang +3
In streaming platforms churn is extremely costly, yet A/B tests are typically evaluated using outcomes observed within a limited experimental horizon. Even when both short- and pre…
Large Causal Models for Temporal Causal Discovery
Nikolaos Kougioulis, Nikolaos Gkorgkolis, MingXue Wang +4
Causal discovery for both cross-sectional and temporal data has traditionally followed a dataset-specific paradigm, where a new model is fitted for each individual dataset. Such an…