When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning Paper • 2602.10560 • Published 1 day ago • 21
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper • 2602.10604 • Published 1 day ago • 137
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning Paper • 2602.10090 • Published 1 day ago • 45
stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S Text Generation • 197B • Updated about 7 hours ago • 11.1k • 126
stepfun-ai/Step-3.5-Flash-FP8 Text Generation • 199B • Updated about 7 hours ago • 17.5k • 44
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning Paper • 2601.05593 • Published Jan 9 • 83
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale Paper • 2508.10711 • Published Aug 14, 2025 • 145