The Verification Horizon: No Silver Bullet for Coding Agent Rewards Paper • 2606.26300 • Published 3 days ago • 34
FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining Paper • 2606.20506 • Published 9 days ago • 28
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Paper • 2606.13473 • Published 16 days ago • 91
The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution Paper • 2601.15075 • Published Feb 5
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence Paper • 2605.26494 • Published May 26 • 41
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published about 1 month ago • 144
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation Paper • 2605.31264 • Published 29 days ago • 119
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation Paper • 2605.31264 • Published 29 days ago • 119
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence Paper • 2605.26494 • Published May 26 • 41
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published about 1 month ago • 144
MMSkills: Towards Multimodal Skills for General Visual Agents Paper • 2605.13527 • Published May 14 • 121
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories Paper • 2605.04036 • Published May 5 • 72
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration Paper • 2605.03042 • Published May 4 • 140
Seedance 2.0: Advancing Video Generation for World Complexity Paper • 2604.14148 • Published Apr 15 • 167
Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization Paper • 2604.09574 • Published Feb 24 • 30