Eduardo Blanco

The paper introduces a novel, training-free method to automatically generate fine-grained evaluation rubrics for LLM-as-a-Judge, and further proposes an iterative fine-tuning strategy that significantly improves rubric quality.

The paper introduces LedgerAgent, an inference-time method for tool-calling agents that maintains observed task states in a separate ledger and checks state-dependent policy constraints before tool calls, improving performance in customer-service domains.