Socio-Foundation: A Model for Generalizable Individual Behavior Simulation via Hierarchical Capability Distillation

Key points

• To overcome these challenges, we organize individual simulation into the FONTS Taxonomy, comprising five complementary capability dimensions: persona fidelity (F), outcome realization (O), behavioral naturalness (N), trajectory coherence (T), and social grounding (S).1
• Grounded in this taxonomy, we curate a standardized training corpus library of approximately 10 million instances across 14 representative datasets and present Socio-Foundation.1
• Socio-Foundation decouples specialization from integration via a three-stage pipeline: learning task experts via DAPO, consolidating them into capability experts via off-policy distillation, and unifying them via multi-teacher on-policy distillation (MOPD).1
• Experiments show that Socio-Foundation outperforms its Qwen3-8B base by 11.0 points and approaches frontier models such as GLM-5.2, with ablations and out-of-distribution evaluations further demonstrating the effectiveness and generalization of our model.1

Sources (1)

• [1]Socio-Foundation: A Model for Generalizable Individual Behavior Simulation via Hierarchical Capability Distillation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 06:31 PM

  Simulating individual behavior requires large language models (LLMs) to preserve persona traits while adapting to dynamic social contexts.

  To overcome these challenges, we organize individual simulation into the FONTS Taxonomy, comprising five complementary capability dimensions: persona fidelity (F), outcome realization (O), behavioral naturalness (N), trajectory coherence (T), and social grounding (S).

Extractive summary: sentences quoted from the sources.