← All IntelClip / AI Tools
Three paradigm stages of role-playing language agents
From The Miranda Hypothesis: How Hamilton Poisoned Persona Evals - Jacob E. Thomas, Results Gen · ≈6:30
A compact map of the literature — rule-based templates, then imitation, then cognitive simulation — that anyone building persona systems can use to place their own approach.
What’s in it
- A compact map of the literature — rule-based templates, then imitation, then cognitive simulation — that anyone building persona systems can use to place their own approach.
Clip transcript
Let me start by situating this in the field's actual research trajectory because it's a story of cumulative progress, not a failure. The survey literature, Chen and colleagues in 2024, Wang and colleagues more recently in 26, trace a clear evolution across three paradigm stages. First, rule-based templates. These are canned responses keyed to inputs. Then imitation. Large models reproducing a figure's voice, cadence, characteristic ticks. And now what the literature calls cognitive simulation. Systems that model personality through psychological frameworks, hold character state and structured memory, and generate behavior through motivational situation chains. Each stage is a genuine advance over the last.
Recommended reads
- clipHow an agent simulation is actually wired upAI Engineer
articleRole Steering of Language Models for Social SimulationsIsaac Song, Mohammed Rehan Parwani, Glenn Matlin, Emile Anand, Akhil Theerthala, Arjun Chatterjee, Maria Kostylew, Yonadav G. Shavit, Sebastien Krier, Mark Riedl
articleLLM Powered Autonomous AgentsLilian Weng
Comments
Checking sign-in…
Loading comments…