LADDER: Self-Improving LLMs Through Recursive Problem Decomposition
Paper
•
2503.00735
•
Published
•
22
RLMs (Reasoning Language Models)
-
-
START: Self-taught Reasoner with Tools
Paper • 2503.04625 • Published • 114 -
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Paper • 2503.05592 • Published • 27 -
R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcing Learning
Paper • 2503.05379 • Published • 39 -
RekaAI/reka-flash-3
21B • Updated • 1.48k • 380 -
RekaAI/VibeEval
Viewer • Updated • 269 • 1.07k • 47 -
Qwen/QwQ-32B
Text Generation • 33B • Updated • 196k • • 2.82k -
open-r1/OlympicCoder-7B
Text Generation • 8B • Updated • 1.08k • • 180 -
open-r1/OlympicCoder-32B
Text Generation • 33B • Updated • 802 • • 156 -
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
Paper • 2503.16219 • Published • 51 -
predibase/Predibase-T2T-32B-RFT
33B • Updated • 31 • 19 -
agentica-org/DeepCoder-1.5B-Preview
Text Generation • 2B • Updated • 1.41k • 66 -
agentica-org/DeepCoder-14B-Preview
Text Generation • 15B • Updated • 27.2k • • 668 -
reasonir/ReasonIR-8B
Feature Extraction • 8B • Updated • 4.38k • 53 -
deepseek-ai/DeepSeek-R1-0528
Text Generation • 685B • Updated • 491k • • 2.34k -
nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
Text Generation • 2B • Updated • 9.73k • 180 -
Haoz0206/Omni-R1
Video-Text-to-Text • 9B • Updated • 295 • 22 -
mistralai/Magistral-Small-2506
Text Generation • 24B • Updated • 47.4k • 590 -
microsoft/Phi-4-mini-reasoning
Text Generation • 4B • Updated • 32.1k • 196 -
microsoft/Phi-4-mini-flash-reasoning
Text Generation • 4B • Updated • 12.5k • 212 -
microsoft/Phi-4-reasoning
Text Generation • 15B • Updated • 8.2k • 200 -
osmosis-ai/Osmosis-Apply-1.7B
Text Generation • 2B • Updated • 500 • 83