Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations
EMNLP 2025 paper introducing PersonaEvolve, an LLM-based optimizer that refines agent personas so crowds of LLM agents behave realistically against expert benchmarks
EMNLP 2025 paper introducing PersonaEvolve, an LLM-based optimizer that refines agent personas so crowds of LLM agents behave realistically against expert benchmarks