MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use Paper • 2509.24002 • Published Sep 28 • 169
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain Paper • 2509.26507 • Published 29 days ago • 516
TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning Paper • 2509.25760 • Published 30 days ago • 53
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training Paper • 2509.25758 • Published 30 days ago • 22
DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively Paper • 2509.26603 • Published 29 days ago • 16
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning Paper • 2509.07980 • Published Sep 9 • 98
Train Long, Think Short: Curriculum Learning for Efficient Reasoning Paper • 2508.08940 • Published Aug 12 • 26
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning Paper • 2509.03646 • Published Sep 3 • 30
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models Paper • 2412.06748 • Published Dec 9, 2024 • 2
ERank Collection A highly effective and efficient pointwise reranker built from a reasoning LLM, which excels across diverse relevance scenarios with low latency • 3 items • Updated Sep 3 • 8
PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts Paper • 2508.09848 • Published Aug 13 • 66