Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper
•
2505.24726
•
Published
•
272
papers-to-read
-
-
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 260 -
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper • 2507.01006 • Published • 236 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 254 -
MemOS: A Memory OS for AI System
Paper • 2507.03724 • Published • 153 -
GUI-G^2: Gaussian Reward Modeling for GUI Grounding
Paper • 2507.15846 • Published • 131 -
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Paper • 2507.16784 • Published • 119 -
WebSailor: Navigating Super-human Reasoning for Web Agent
Paper • 2507.02592 • Published • 118 -
4KAgent: Agentic Any Image to 4K Super-Resolution
Paper • 2507.07105 • Published • 101 -
ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents
Paper • 2507.22827 • Published • 98 -
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
Paper • 2508.01191 • Published • 236 -
DINOv3
Paper • 2508.10104 • Published • 261 -
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Paper • 2508.06471 • Published • 181 -
VeriGUI: Verifiable Long-Chain GUI Dataset
Paper • 2508.04026 • Published • 157 -
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
Paper • 2508.05629 • Published • 176 -
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 149 -
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Paper • 2509.08721 • Published • 617 -
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code
Paper • 2508.18106 • Published • 340 -
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Paper • 2509.02547 • Published • 206 -
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 166 -
A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
Paper • 2508.21148 • Published • 140 -
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 178 -
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 96 -
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research
Paper • 2509.13312 • Published • 100 -
Scaling Agents via Continual Pre-training
Paper • 2509.13310 • Published • 103 -
WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
Paper • 2509.06501 • Published • 77 -
Towards a Unified View of Large Language Model Post-Training
Paper • 2509.04419 • Published • 73 -
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
Paper • 2509.01055 • Published • 69 -
MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML
Paper • 2509.06806 • Published • 61 -
FlowRL: Matching Reward Distributions for LLM Reasoning
Paper • 2509.15207 • Published • 100