Tag
This paper investigates entity tracking in language models and humans using naturalistic narratives, revealing that models with sub-billion parameters already achieve human-level performance and exceed humans, indicating that core language understanding emerges at smaller scales than previously assumed.
StainFlow introduces an entity-stain-flow process reward model for GUI agents, using global entity stain tracking and local evidence linking to improve credit assignment in reinforcement learning, achieving 3.2% relative improvement on AndroidWorld.