Dual Exam: Controlled Evaluation of Multimodal Agents and World Models Paper • 2610.31066 • Published 28 days ago • 25
ClawLoop: Self-Improving Agents via Harness-Native Training Loop Paper • 2610.14118 • Published Oct 9 • 28
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models Paper • 2609.08418 • Published Sep 8 • 34
Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training Paper • 2608.02391 • Published Aug 3 • 3
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design Paper • 2605.08756 • Published May 9 • 23
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published Apr 24 • 151
V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models Paper • 2511.16668 • Published Nov 20, 2025 • 56