Jia Wang

This work extends SocioVerse 1.0 into a human-AI co-evolutionary paradigm built from two loops and one infrastructure, and validates SocioVerse2 across three case families and seven case studies, from reproducing canonical agent-based models to modeling policy processes on real records and nowcasting macro-economic indices beyond the response model's knowledge cutoff.

OnPanda is presented, an interactive tool for efficiently annotating LLM alignment data and agent trajectories that adopts token-level correction as its core interaction and releases Panda-CVL, a dataset annotated with onPanda, together with a benchmark for token-level correction.

HiLaR reveals that optimizing user preference modeling through hierarchical latent reasoning can significantly outperform traditional recommendation approaches.

ConsumerSim reveals that consumer confidence is driven more by individual interpretations of salient events than by aggregate trends, transforming our understanding of economic sentiment dynamics.

A new robustness metric based on Fisher Information reveals critical insights into model sensitivity and adversarial vulnerability across popular architectures.

Current mobile GUI agents are surprisingly inept at everyday smartphone tasks, achieving only 62% success on a new benchmark of real-world Android apps.

Forget noisy pseudo-labels: SpatialEvo unlocks self-supervised 3D spatial reasoning by generating perfectly accurate training data directly from scene geometry.