Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Paper
•
2503.24290
•
Published
•
62
To Read collection
interesting papers to read
-
-
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 118 -
START: Self-taught Reasoner with Tools
Paper • 2503.04625 • Published • 114 -
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Paper • 2503.14476 • Published • 128 -
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Paper • 2503.07536 • Published • 86 -
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
Paper • 2503.16219 • Published • 51 -
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Paper • 2502.14499 • Published • 192 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 153 -
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 141 -
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Paper • 2502.18449 • Published • 74 -
Competitive Programming with Large Reasoning Models
Paper • 2502.06807 • Published • 70 -
S*: Test Time Scaling for Code Generation
Paper • 2502.14382 • Published • 63 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 398 -
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper • 2501.04519 • Published • 279 -
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper • 2501.12599 • Published • 117 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 122 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 106 -
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Paper • 2501.05366 • Published • 101 -
Humanity's Last Exam
Paper • 2501.14249 • Published • 75 -
Agent Laboratory: Using LLM Agents as Research Assistants
Paper • 2501.04227 • Published • 92 -
Training Large Language Models to Reason in a Continuous Latent Space
Paper • 2412.06769 • Published • 86 -
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper • 2411.04905 • Published • 125 -
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Paper • 2411.10442 • Published • 80 -
Large Language Models Can Self-Improve in Long-context Reasoning
Paper • 2411.08147 • Published • 67 -
Agentic Knowledgeable Self-awareness
Paper • 2504.03553 • Published • 28 -
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Paper • 2504.01990 • Published • 284 -
AFlow: Automating Agentic Workflow Generation
Paper • 2410.10762 • Published -
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Paper • 2504.10479 • Published • 266 -
Iterative Self-Training for Code Generation via Reinforced Re-Ranking
Paper • 2504.09643 • Published • 34 -
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
Paper • 2504.11536 • Published • 61 -
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
Paper • 2504.10481 • Published • 84 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 127 -
FlowReasoner: Reinforcing Query-Level Meta-Agents
Paper • 2504.15257 • Published • 46 -
TTRL: Test-Time Reinforcement Learning
Paper • 2504.16084 • Published • 112 -
ToolRL: Reward is All Tool Learning Needs
Paper • 2504.13958 • Published • 44 -
LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs
Paper • 2504.14655 • Published • 19 -
Self-Taught Evaluators
Paper • 2408.02666 • Published • 30 -
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
Paper • 2504.06261 • Published • 110 -
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper • 2504.17192 • Published • 110 -
Learning to Reason under Off-Policy Guidance
Paper • 2504.14945 • Published • 85 -
Video-R1: Reinforcing Video Reasoning in MLLMs
Paper • 2503.21776 • Published • 78 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 293 -
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 151 -
Differential Transformer
Paper • 2410.05258 • Published • 179 -
Pixtral 12B
Paper • 2410.07073 • Published • 66 -
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
Paper • 2504.03160 • Published • 1 -
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
Paper • 2504.16656 • Published • 57 -
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Paper • 2504.21776 • Published • 55 -
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Paper • 2504.20571 • Published • 93 -
Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models
Paper • 2504.20157 • Published • 37 -
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 168 -
Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
Paper • 2505.01441 • Published • 36 -
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
Paper • 2505.22617 • Published • 109 -
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 83 -
NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
Paper • 2505.16938 • Published • 113 -
AdaptThink: Reasoning Models Can Learn When to Think
Paper • 2505.13417 • Published • 78 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 101 -
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Paper • 2505.24863 • Published • 73 -
HardTests: Synthesizing High-Quality Test Cases for LLM Coding
Paper • 2505.24098 • Published • 39