FCMBench: A Comprehensive Financial Credit Multimodal Benchmark for Real-world Applications Paper • 2601.00150 • Published Jan 1 • 1
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent Paper • 2606.30616 • Published Jun 29 • 104
DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning Paper • 2610.07835 • Published Oct 6 • 1
Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards Paper • 2602.02555 • Published Jan 30 • 6