generative agents 1human annotation 1long-horizon decision making 1social simulation 1step-level preference learning 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.AI2026
Step-Level Preference Learning for Generative Agents in Social Simulations
Wenchang Gao, Pingyue Sheng, Lanlan Qiu +7
The paper presents an interactive interface to collect step‑level human preference data for generative agents, creates a 57K annotation dataset, and shows that training LLMs with t…
cs.CL2026
Learning Stateful Predictive Knowledge From Experience
Yan Song, Xidong Feng, Bo Liu +7
As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights. Viewed through the lens of predicti…