Shaleen Deep

works on

anomaly detection 1 failure attribution 1 LLM agents 1 neural controlled differential equations 1 one-class learning 1

From the 1 of 8 linked papers with an AI index.

activity

20242026

collaborators

Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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…