Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning Paper • 2510.08146 • Published Oct 9, 2025 • 1
EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages Paper • 2603.09678 • Published 5 days ago • 1
The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute Paper • 2511.02309 • Published Nov 4, 2025 • 4
view article Article System Prompt Learning: Teaching LLMs to Learn Problem-Solving Strategies from Experience Jun 2, 2025 • 24
Running 3.74k The Ultra-Scale Playbook 🌌 3.74k The ultimate guide to training LLM on large GPU Clusters