Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 135
Papers
-
-
Magistral
Paper • 2506.10910 • Published • 68 -
Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs
Paper • 2506.07240 • Published • 7 -
Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
Paper • 2506.09991 • Published • 55 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 265 -
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
Paper • 2506.06941 • Published • 16 -
s3: You Don't Need That Much Data to Train a Search Agent via RL
Paper • 2505.14146 • Published • 20 -
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Paper • 2506.11763 • Published • 74 -
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Paper • 2506.14245 • Published • 45 -
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 • 51 -
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Paper • 2507.00432 • Published • 79 -
Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
Paper • 2507.14241 • Published • 18 -
WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
Paper • 2507.15061 • Published • 60 -
Qwen3 Technical Report
Paper • 2505.09388 • Published • 339 -
Replacing thinking with tool usage enables reasoning in small language models
Paper • 2507.05065 • Published • 16 -
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 • 68 -
Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
Paper • 2508.10751 • Published • 29 -
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
Paper • 2508.14704 • Published • 43 -
Deep Think with Confidence
Paper • 2508.15260 • Published • 90 -
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 162 -
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications
Paper • 2508.16279 • Published • 61 -
InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles
Paper • 2508.16072 • Published • 4 -
Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
Paper • 2508.18076 • Published • 6 -
Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation
Paper • 2410.20774 • Published -
Provable Benefits of In-Tool Learning for Large Language Models
Paper • 2508.20755 • Published • 11 -
OpenClaw-RL: Train Any Agent Simply by Talking
Paper • 2603.10165 • Published • 150