LLM agents are widely used in social simulation, yet fluent social reasoning does not guarantee valid decision mechanisms. We test whether models implement socially embedded utility, where actions depend on peer-weighted references rather than isolated private preference. We introduce a theory-guided benchmark from network utility theory covering utility recovery, social-comparison gating, and structural transfer across two out-of-distribution decision forms. Across open-source and proprietary models, we find a gap between cue recognition and peer aggregation, spurious social activation when comparison should be inactive, and declining accuracy as social dependence rises. We propose theory-supervised mechanism alignment trained on latent utility states. Fine-tuning yields +8.3 and +13.9 utility-recovery points on Llama-3.1-8B and Qwen3-8B, raises gating above 95%, and improves transfer to unseen structures. Multi-agent simulations show that repairing local utility shifts macro outcomes, including stronger financial amplification and more stable labor stratification, which indicates that realistic macro-level simulations require adjustments at the individual level. Data and code are available at https://github.com/saaranLiu/SEDM-alignment.

Recent progress in generative language models has enabled machines to generate astonishingly realistic texts. While there are many legitimate applications of such models, there is also a rising need to distinguish machine-generated texts from human-written ones (e.g., fake news detection). However, to our best knowledge, there is currently no benchmark environment with datasets and tasks to systematically study the so-called ”Turing Test” problem for neural text generation methods. In this work, we present the TURINGBENCH benchmark environment, which is comprised of (1) a dataset with 200K human- or machine-generated samples across 20 labels Human, GPT-1, GPT-2_small, GPT-2_medium, GPT-2_large,GPT-2_xl, GPT-2_PyTorch, GPT-3, GROVER_base, GROVER_large, GROVER_mega, CTRL, XLM, XLNET_base, XLNET_large, FAIR_wmt19, FAIR_wmt20, TRANSFORMER_XL, PPLM_distil, PPLM_gpt2, (2) two benchmark tasks–i.e., Turing Test (TT) and Authorship Attribution (AA), and (3) a website with leaderboards. Our preliminary experimental results using TURINGBENCH show that GPT-3 and FAIR_wmt20 are the current winners, among all language models tested, in generating the most human-like indistinguishable texts with the lowest F1 score by five state-of-the-art TT detection models. The TURINGBENCH is available at: https://turingbench.ist.psu.edu/