AI
GIM: Evaluating models via tasks that integrate multiple cognitive domains
Researchers have introduced a new benchmark called the Grounded Integration Measure (GIM) to evaluat...
AI
TO-Agents: A Multi-Agent AI Framework for Subjective Preference-Guided Topology Optimization
Researchers have developed a framework called TO-Agents that connects human design intent with topol...
AI
Designing Benchmarks for Knowledge Work
Researchers propose a new framework for designing benchmarks for AI systems that perform knowledge w...
AI
MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition
Researchers have introduced MOSAIC, a framework for structured agentic intelligence and composition ...
AI
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Researchers have proposed a new framework called Latent Reward Steering (LRS) to...
AI
MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
Researchers propose the MindHelper Challenge to evaluate a robot's ability to co...
AI
Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification
Researchers have developed a new reward-modeling procedure called Expected Value...
AI
Zero knowledge verification for frontier AI training is possible
Researchers have proposed a method to verify the training of frontier AI models ...