SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution

arXiv:2603.23406v1 Announce Type: new Abstract: While large language models simulate social behaviors, their capacity for stable stance formation and identity negotiation during

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

arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to

arXiv:2608.13787v1 Announce Type: new Abstract: AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over

arXiv:2605.11556v1 Announce Type: new Abstract: Solving complex long-horizon tasks requires strong planning and reasoning capabilities. Although datasets with explicit

arXiv:2607.18255v1 Announce Type: new Abstract: Contribution attribution has become a central problem in LLM-based multi-agent systems, where final outputs are produced through

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:2605.15768v1 Announce Type: new Abstract: Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn