CORTEXA
← Browse
arxivcs.AI2026-07-16

Step-Level Preference Learning for Generative Agents in Social Simulations

Wenchang Gao, Pingyue Sheng, Lanlan Qiu, Yunfei Ma, Jian Zhao, Baicheng Chen, Kangda Wang, Yuyang Tian, Shunqiang Mao, Tianxing He

Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action selection. However, fine-grained human annotations of these intermediate steps remain scarce, and existing agents are not grounded in human preferences over such intermediate decisions. To address this gap, we introduce \method, an interactive simulation interface that enables us to collect step-level human preference supervision over agent decision trajectories, leading to a dataset of 57K fine-grained annotations. We conduct step-level preference learning on open-weight language models using supervised finetuning and direct preference optimization on this data, consistently improving simulation fidelity, coordination, and interaction quality, and inducing more socially effective agent behavior. Our results show that step-level human supervision is an effective training signal for improving both local decision quality and long-horizon agent behavior.

View free PDFSource page

Related papers

arxivcs.AI2026-07-14

Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents

Yaopei Zeng, Congchao Wang, JianHang Chen, Nan Wang, Yurui Chang, Lu Lin

LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed. Reliable deployment therefore…

View free PDFSource page
arxivcs.AI2026-07-06

Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models

Raj Jaiswal, Dhruv Jain, Rishabh Dhawan, Sree Krishna Uppalapati, Shin'ichi Satoh, Tanuja Ganu, et al.

Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows. Limited domain knowledge, hallucination under multi-step derivation, and distributional sensitivity compound this failure. We propose a…

View free PDFSource page
arxivcs.MAcs.AIcs.SIphysics.soc-ph2026-07-15

Social Simulations: from Agent-Based Modeling to Digital Twins

Erica Cau, Andrea Failla, Valentina Pansanella, Giulio Rossetti

This book chapter covers the evolution of social simulation from classical agent-based models, in which agents interact according to explicitly defined behavioral rules, to AI-enhanced simulations based on Large Language Models and, ultimately, Social Digital Twins: high-fidelity…

View free PDFSource page
arxivcs.CLcs.AIcs.SI2026-07-07

From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

Shiyi Ling, Zhi Zheng, Hui Zheng, Wenjun Xue, Feng Ye, Tong Xu

Putnam's Social Capital Theory is a foundational framework for collective action and community prosperity. However, traditional empirical methods face practical limits on control and replication. Meanwhile, LLM-based social simulations are typically behavior-driven and lack theor…

View free PDFSource page
arxivcs.AIcs.LG2026-07-14

Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models

Ilias Kazantzidis, Timothy J. Norman, Yali Du, Christopher T. Freeman

We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown and no suitable reward function is available. In the context of safety-critical environments, we consider traditional reinforceme…

View free PDFSource page