Large language models reorganize representational geometry during in-context learning

ArXi:2605.28854v1 Announce Type: cross Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a capability known as in-context learning (ICL). Prior work on synthetic tasks has shown that ICL can implement specific algorithms, nstrating architectural competence, and mechanistic analyses have identified key circuits that this behavior.