Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published 3 days ago • 277
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up Paper • 2609.13443 • Published 6 days ago • 8
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Paper • 2609.13356 • Published 6 days ago • 302
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation Paper • 2609.11115 • Published 7 days ago • 202
view article Article Making open-source AI weather forecasting models easy to run hugging-science • 8 days ago • 31
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 9 days ago • 419
StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean Paper • 2609.09264 • Published 9 days ago • 9
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 9 days ago • 419 • 8
SwarmWorld: Stigmergic technological evolution in societies of language-model agents Paper • 2608.26081 • Published 22 days ago • 1
Agent Memory Is a Surface for Endogenous Authorization Laundering Paper • 2609.01836 • Published 16 days ago • 7
Evaluating the Hidden Costs of Personalization in Large Language Models Paper • 2608.28833 • Published 20 days ago • 30
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability Paper • 2608.30320 • Published 17 days ago • 59