paperJanuary 2026Unreviewed

Trajectory Guard - A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI

Laksh Advani

arXiv.org

Abstract

Autonomous LLM agents generate multi-step action plans that can fail due to contextual misalignment or structural incoherence. Existing anomaly detection methods are ill-suited for this challenge: mean-pooling embeddings dilutes anomalous steps, while contrastive-only approaches ignore sequential structure. Standard unsupervised methods on pre-trained embeddings achieve F1-scores no higher than 0.69. We introduce Trajectory Guard, a Siamese Recurrent Autoencoder with a hybrid loss function that

Cite

@misc{advani2026trajectory,
  title = {{Trajectory Guard - A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI}},
  author = {Laksh Advani},
  year = {2026},
  month = jan,
  eprint = {2601.00516},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2601.00516},
  url = {https://www.semanticscholar.org/paper/97bdc0f37dea8f7846218aaffa48f5752ef2e971}
}