Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Mul

arXiv:2605.08354v1 Announce Type: new Abstract: Aligning multimodal generative models with human preferences demands reward signals that respect the compositional,

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical

arXiv:2603.18363v1 Announce Type: cross Abstract: Unsupervised Reinforcement Learning from Internal Feedback (RLIF) has emerged as a promising paradigm for eliciting the latent

arXiv:2605.29042v1 Announce Type: new Abstract: Human coordination often relies on the ability to influence the beliefs of others through strategic action. In multi-agent

arXiv:2603.29871v1 Announce Type: new Abstract: In user-agent interaction scenarios such as recommendation, brainstorming, and code suggestion, Large Language Models (LLMs) often

arXiv:2604.18982v1 Announce Type: new Abstract: Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language