4 papers
Near-Miss: Latent Policy Failure Detection in Agentic Workflows
Ella Rabinovich, David Boaz, Naama Zwerdling +1
Agentic systems for business process automation often require compliance with policies governing conditional updates to the system state. Evaluation of policy adherence in LLM-base…
Towards Enforcing Company Policy Adherence in Agentic Workflows
Naama Zwerdling, David Boaz, Ella Rabinovich +3
Large Language Model (LLM) agents hold promise for a flexible and scalable alternative to traditional business process automation, but struggle to reliably follow complex company p…
On the Robustness of Agentic Function Calling
Ella Rabinovich, Ateret Anaby-Tavor
Large Language Models (LLMs) are increasingly acting as autonomous agents, with function calling (FC) capabilities enabling them to invoke specific tools for tasks. While prior res…
A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios
Samuel Ackerman, Ella Rabinovich, Eitan Farchi +1
We evaluate the robustness of several large language models on multiple datasets. Robustness here refers to the relative insensitivity of the model's answers to meaning-preserving…