Physics-Guided Conditional Diffusion Model for Rare Event Synthesis and Diagnosis for the Water-Gas Shift ReactionResearchSep 30, 2026
Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent EnvironmentsResearchSep 30, 2026
PowerMarketJax: A JAX Benchmark Suite for Multi-Agent Reinforcement Learning in Power MarketsResearchSep 30, 2026
Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime GovernanceResearchSep 30, 2026
Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute ScalingResearchSep 30, 2026