Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot CoordinationResearchOct 2, 2026
Tight Transition Time Bounds for Separable Logistic Regression at the Edge of StabilityResearchOct 2, 2026
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse LanguagesResearchOct 2, 2026
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language ModelsResearchOct 2, 2026
Aligned but Not Partner-Specific: How Multimodal LLM Agents Succeed in Reference Games Without Forming Conceptual PactsResearchOct 2, 2026
Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement LearningResearchOct 2, 2026
Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research TrajectoryResearchOct 2, 2026