每天自动聚合 AI 领域最新动态
Question answering has advanced rapidly with large language models, but predominantly for high-resource languages, in...
Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses...
Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information need...
LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation se...
Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer...
Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specificati...
Effective troubleshooting agents in enterprise customer support depend on retrieving actionable guidance from similar...
Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark tas...
Generative agents are increasingly used to select and narrate video highlights, but they typically operate over unstr...
Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet exis...
Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores acros...
Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motiv...