GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning Paper • 2602.12099 • Published Feb 12 • 61
When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning Paper • 2602.10560 • Published Feb 11 • 30
G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design Paper • 2602.08253 • Published Feb 9 • 26
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression Paper • 2602.11008 • Published Feb 11 • 18
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning Paper • 2602.08234 • Published Feb 9 • 72
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild Paper • 2603.17187 • Published 10 days ago • 131
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding Paper • 2603.19235 • Published 8 days ago • 92
MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning Paper • 2603.16929 • Published 14 days ago • 12
A Subgoal-driven Framework for Improving Long-Horizon LLM Agents Paper • 2603.19685 • Published 8 days ago • 18
Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck Paper • 2603.08462 • Published 18 days ago • 21
Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States Paper • 2603.19987 • Published 7 days ago • 9
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation Paper • 2603.23500 • Published 3 days ago • 33
InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning Paper • 2602.06960 • Published Feb 6 • 14