Guided Self-Evolving LLMs with Minimal Human Supervision
Paper • 2512.02472 • Published • 55
Ai-general
-
-
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Paper • 2509.25454 • Published • 148 -
Video Reasoning without Training
Paper • 2510.17045 • Published • 8 -
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 276 -
RLP: Reinforcement as a Pretraining Objective
Paper • 2510.01265 • Published • 45 -
Large Reasoning Models Learn Better Alignment from Flawed Thinking
Paper • 2510.00938 • Published • 60 -
LiveTradeBench: Seeking Real-World Alpha with Large Language Models
Paper • 2511.03628 • Published • 13 -
PromptBridge: Cross-Model Prompt Transfer for Large Language Models
Paper • 2512.01420 • Published • 11 -
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Paper • 2510.09577 • Published • 8 -
Diversity Has Always Been There in Your Visual Autoregressive Models
Paper • 2511.17074 • Published • 8 -
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Paper • 2511.13254 • Published • 139 -
Search Self-play: Pushing the Frontier of Agent Capability without Supervision
Paper • 2510.18821 • Published • 19 -
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 • 117 -
Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
Paper • 2511.16043 • Published • 110 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 25 -
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
Paper • 2509.08755 • Published • 57 -
gpt-oss-120b & gpt-oss-20b Model Card
Paper • 2508.10925 • Published • 17 -
OpenAI o1 System Card
Paper • 2412.16720 • Published • 37 -
Self-Improving VLM Judges Without Human Annotations
Paper • 2512.05145 • Published • 20 -
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 • 1 -
MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning
Paper • 2511.06805 • Published • 13 -
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 • 76 -
DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
Paper • 2512.03000 • Published • 37 -
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
Paper • 2512.04926 • Published • 42 -
Voxify3D: Pixel Art Meets Volumetric Rendering
Paper • 2512.07834 • Published • 45 -
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
Paper • 2512.07461 • Published • 79 -
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
Paper • 2512.13586 • Published • 93 -
RePo: Language Models with Context Re-Positioning
Paper • 2512.14391 • Published • 12 -
Universal Reasoning Model
Paper • 2512.14693 • Published • 44 -
MMGR: Multi-Modal Generative Reasoning
Paper • 2512.14691 • Published • 121 -
Next-Embedding Prediction Makes Strong Vision Learners
Paper • 2512.16922 • Published • 89 -
Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers
Paper • 2512.17351 • Published • 28 -
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
Paper • 2512.14052 • Published • 42 -
CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion
Paper • 2512.19535 • Published • 12 -
SemanticGen: Video Generation in Semantic Space
Paper • 2512.20619 • Published • 94 -
LongVideoAgent: Multi-Agent Reasoning with Long Videos
Paper • 2512.20618 • Published • 56 -
Multi-hop Reasoning via Early Knowledge Alignment
Paper • 2512.20144 • Published • 7 -
Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
Paper • 2512.21004 • Published • 13 -
TimeBill: Time-Budgeted Inference for Large Language Models
Paper • 2512.21859 • Published • 25 -
SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents
Paper • 2512.22322 • Published • 39 -
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 153 -
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
Paper • 2601.03193 • Published • 49 -
Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models
Paper • 2601.01321 • Published • 20 -
LLM-in-Sandbox Elicits General Agentic Intelligence
Paper • 2601.16206 • Published • 86 -
Learning to Discover at Test Time
Paper • 2601.16175 • Published • 44 -
Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
Paper • 2601.17058 • Published • 190