Do Reasoning LLMs Refuse What They Infer in Long Contexts?

ArXi:2602.08874v2 Announce Type: replace Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed across a context and become visible only after the model composes the relevant pieces. Existing safety evaluations mostly test explicit harmful requests, and therefore miss this failure mode. We