SOURCE-LINKED INTELLIGENCE

K-Bench: A Benchmark for LLM Unlearning in Agentic Deployments

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Unlearning benchmarks such as TOFU and MUSE certify forgetting by reading the model's final answer, where a model that refuses to answer already counts as having forgotten. We show that this model-level certificate does not transfer once the model is deployed as an agent. We introduce K-Bench, a benchmark that scores LLM unlearning under agentic deployment. K-Bench inspects all six channels a ReAct agent exposes, including its chain-of-thought (CoT), tool calls and tool observations, and elicited summary. A query counts as leaked if the secret appears in any of them. Each experiment places the

Read original source ↗ Open in workspace

recordType

paper

region

Global