Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas

ArXi:2605.09159v1 Announce Type: new Recent work shows that large language models (LLMs) encode behavioural traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has used such directions as static handles for behavioural steering. Building on this, we treat them as dynamic signals instead: probes we can monitor and intervene on as reasoning unfolds. We use the term polylogue to denote the time series of alignments between persona vectors and hidden activations over the.