arXiv AI June 17, 2026 By Keane Ong, Sabri Boughorbel, Luwei Xiao, Chanakya Ekbote, Wei Dai, Ao Qu, Jingyao Wu, Rui Mao, Ehsan Hoque, Erik Cambria, Gianmarco Mengaldo, Paul Pu Liang

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization

Read the original on arXiv AI →

arXiv:2602. 10635v3 Announce Type: replace Abstract: Socially intelligent AI systems must reason across diverse human behavioral tasks and generalize to new social contexts.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 10

Social World Models

arXiv:2509. 00559v3 Announce Type: replace Abstract: Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited information.

By Xuhui Zhou, Jiarui Liu, Akhila Yerukola, Hyunwoo Kim, Maarten Sap

llms agents benchmarks

arXiv Machine Learning

Jun 5

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.

By Kaichen He, Zihao Wang, Muyao Li, Anji Liu, Yitao Liang

agents reinforcement-learning robotics fine-tuning benchmarks

arXiv AI

Jul 17

Step-Level Preference Learning for Generative Agents in Social Simulations

arXiv:2607. 14485v1 Announce Type: new Abstract: 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.

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

llms agents fine-tuning

arXiv Machine Learning

Jun 18

Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents

arXiv:2606. 18537v1 Announce Type: new Abstract: Humans often acquire new skills by observing others, since observed behaviors implicitly reveal how to act in an environment.

By Caleb Chang, Davin Win Kyi, Natasha Jaques, Karen Leung

agents robotics fine-tuning safety

arXiv Machine Learning

Jun 25

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).

By Aleksandar Vujinovic, Aleksandar Kovacevic

rag diffusion

arXiv AI

Aug 7

A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition

arXiv:2608. 05673v1 Announce Type: new Abstract: Trajectory prediction has shifted toward structured formulations with explicit social modeling.

By Jiaheng Chen, Jiaxing Li, Tinghe Zhang, Chaopeng Guo

agents benchmarks

Related stories

Social World Models

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

Step-Level Preference Learning for Generative Agents in Social Simulations

Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition