Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 77
Nice papers
-
-
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Paper • 2610.14118 • Published • 19 -
Latent World Action Model for GUI Agents
Paper • 2610.14228 • Published • 12 -
Jeva: System One Models from First Principles
Paper • 2610.18773 • Published • 264 -
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
Paper • 2610.13912 • Published • 43 -
AutoDev: Automated AI-Driven Development
Paper • 2403.08299 • Published • 25 -
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Paper • 2609.18063 • Published • 27 -
TradingAgents: Multi-Agents LLM Financial Trading Framework
Paper • 2412.20138 • Published • 151 -
Multics: Generative Multi-Player World Model with Hierarchical Communication
Paper • 2610.17201 • Published • 55 -
Kronos: A Foundation Model for the Language of Financial Markets
Paper • 2508.02739 • Published • 59 -
Prime Agent: A Self-Improving RLM Harness
Paper • 2608.23552 • Published • 57 -
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
Paper • 2604.27393 • Published • 67 -
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
Paper • 2509.18154 • Published • 63 -
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
Paper • 2610.15782 • Published • 25 -
Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution
Paper • 2609.35855 • Published • 10 -
UniMate: One Unified Model to Animate Diverse Skeletons
Paper • 2609.05415 • Published • 24 -
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Paper • 2608.16157 • Published • 113