controlled-differential-equations

Tag

Cards List
#controlled-differential-equations

Tracing Agentic Failure from the Flow of Success

arXiv cs.AI · 2026-07-15 Cached

Presents Oat, a lightweight unsupervised method for identifying error steps in LLM-based agentic failure trajectories using neural controlled differential equations trained only on successful trajectories. It achieves 200-5000x speedup over prompting baselines with significant F1 improvements in in-domain and out-of-distribution settings.

0 favorites 0 likes
← Back to home

Submit Feedback