4 papers
Tracing Agentic Failure from the Flow of Success
Samuel Yeh, Yiwen Zhu, Shaleen Deep +1
The paper introduces OAT, a lightweight unsupervised method that learns from successful LLM agent trajectories and detects error steps in failed runs by scoring deviations using ne…
GraphMind: From Operational Traces to Self-Evolving Workflow Automation
Yiwen Zhu, Joyce Cahoon, Anna Pavlenko +13
Complex operational workflows coordinating personnel, tools, and information are central to system operations, yet end-to-end automation remains challenging due to extensive human…
ENCO: Life-Cycle Management of Enterprise-Grade Copilots
Yiwen Zhu, Mathieu Demarne, Kai Deng +12
Software engineers frequently grapple with the challenge of accessing disparate documentation and telemetry data, including TroubleShooting Guides (TSGs), incident reports, code re…
FLAIR: Feedback Learning for Adaptive Information Retrieval
William Zhang, Yiwen Zhu, Yunlei Lu +7
Recent advances in Large Language Models (LLMs) have driven the adoption of copilots in complex technical scenarios, underscoring the growing need for specialized information retri…