Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper
•
2506.06395
•
Published
•
128
Papers
-
-
Magistral
Paper • 2506.10910 • Published • 63 -
Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs
Paper • 2506.07240 • Published • 6 -
Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
Paper • 2506.09991 • Published • 56 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 253 -
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
Paper • 2506.06941 • Published • 14 -
s3: You Don't Need That Much Data to Train a Search Agent via RL
Paper • 2505.14146 • Published • 18 -
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Paper • 2506.11763 • Published • 69 -
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Paper • 2506.14245 • Published • 40 -
Reasoning with Exploration: An Entropy Perspective
Paper • 2506.14758 • Published • 30 -
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Paper • 2506.24119 • Published • 46 -
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Paper • 2507.00432 • Published • 72 -
Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
Paper • 2507.14241 • Published • 16 -
WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
Paper • 2507.15061 • Published • 47 -
Qwen3 Technical Report
Paper • 2505.09388 • Published • 270 -
Replacing thinking with tool usage enables reasoning in small language models
Paper • 2507.05065 • Published • 14 -
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
Paper • 2507.13158 • Published • 24 -
Deep Researcher with Test-Time Diffusion
Paper • 2507.16075 • Published • 53