AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security Paper • 2601.18491 • Published 1 day ago • 31
Geometrically-Constrained Agent for Spatial Reasoning Paper • 2511.22659 • Published Nov 27, 2025 • 41
FlowRL: Matching Reward Distributions for LLM Reasoning Paper • 2509.15207 • Published Sep 18, 2025 • 116
A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports Paper • 2510.02190 • Published Oct 2, 2025 • 19