PolicyBank enables LLM agents to iteratively refine structured policy insights from corrective feedback, closing up to 82% of the performance gap on policy-ambiguity scenarios where prior memory methods achieve near-zero success.
Tests whether the agent applies the clarification correctly under cognitive load
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PolicyBank: Evolving Policy Understanding for LLM Agents
PolicyBank enables LLM agents to iteratively refine structured policy insights from corrective feedback, closing up to 82% of the performance gap on policy-ambiguity scenarios where prior memory methods achieve near-zero success.