TAO improves scheduling for LLM agent services by considering tool readiness and using dynamic programming to place sessions, ...

VibeVideoBench evaluates multimodal agents that generate videos via code, finding that top systems meet core requirements on ...

We ask what a policy learns from its harness and what survives when the harness changes. Under KL-regularized control, we ...

Prox replaces calibrated thresholds with top-k channel selection and a weight-derived reader to accelerate Mixture-of-Experts ...

ThinkWorld improves robotic generalization by representing actions as dynamics chains and using world imagination to learn ...

Hy-Nomas is a video world model that uses causal attention and structured captions to follow multi-turn text and camera ...

Rollback improves robot policies by using world models to rewind to past decisions, explore counterfactual actions, and ...

A world model predicts machine learning program outcomes to enable affordable test-time scaling for AI research agents, ...

CREDIT improves language model self-attribution of external information via counterfactual training, reducing false ...

StreamVibe introduces a benchmark, streaming vision-language model, and hierarchical memory harness to enable proactive, ...

Optimized unmasking policies for masked diffusion language models improve efficiency by using trajectory-contraction targets ...

Reinforcement learning improves reasoning accuracy without requiring a specific wait marker, which originates from training ...