Guided Self-Evolving LLMs with Minimal Human Supervision
Paper
•
2512.02472
•
Published
•
48
Ai-general
-
-
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Paper • 2509.25454 • Published • 140 -
Video Reasoning without Training
Paper • 2510.17045 • Published • 7 -
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 266 -
RLP: Reinforcement as a Pretraining Objective
Paper • 2510.01265 • Published • 40 -
Large Reasoning Models Learn Better Alignment from Flawed Thinking
Paper • 2510.00938 • Published • 58 -
LiveTradeBench: Seeking Real-World Alpha with Large Language Models
Paper • 2511.03628 • Published • 11 -
PromptBridge: Cross-Model Prompt Transfer for Large Language Models
Paper • 2512.01420 • Published • 8 -
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Paper • 2510.09577 • Published • 7 -
Diversity Has Always Been There in Your Visual Autoregressive Models
Paper • 2511.17074 • Published • 7 -
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Paper • 2511.13254 • Published • 134 -
Search Self-play: Pushing the Frontier of Agent Capability without Supervision
Paper • 2510.18821 • Published • 17 -
Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning
Paper • 2510.03259 • Published • 57 -
Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
Paper • 2510.19338 • Published • 114 -
Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
Paper • 2511.16043 • Published • 105 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 24 -
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
Paper • 2509.08755 • Published • 56 -
gpt-oss-120b & gpt-oss-20b Model Card
Paper • 2508.10925 • Published • 12 -
OpenAI o1 System Card
Paper • 2412.16720 • Published • 36 -
Self-Improving VLM Judges Without Human Annotations
Paper • 2512.05145 • Published • 15 -
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique
Paper • 2511.09067 • Published • 2 -
Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
Paper • 2510.23038 • Published -
MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning
Paper • 2511.06805 • Published • 12 -
JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation
Paper • 2511.15958 • Published • 1 -
VeriSciQA: An Auto-Verified Dataset for Scientific Visual Question Answering
Paper • 2511.19899 • Published -
TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
Paper • 2512.05150 • Published • 59