StartLux-Decision-v1.1 AutoThink Collection v1.1, October 2026. Read-or-Think: one-pass answer, a short thought only when unsure. 4B, 9B, 27B. • 13 items • Updated Oct 14 • 9
StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions Paper • 2610.17309 • Published Oct 12 • 30
DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems Paper • 2610.28522 • Published 27 days ago • 26
StartLux-Decision-v1 Collection Typed decision models from 0.8B to 27B. Every question comes back with a probability for each option. • 21 items • Updated Oct 10 • 13
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus Paper • 2608.12149 • Published Aug 12 • 23