The Landscape of Agentic Reinforcement Learning for LLMs: A Survey Paper • 2509.02547 • Published 6 days ago • 164
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code Paper • 2508.18106 • Published 14 days ago • 213
view article Article Welcome EmbeddingGemma, Google's new efficient embedding model By tomaarsen and 5 others • 5 days ago • 170
Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral Protocol Paper • 2508.17068 • Published 16 days ago • 3
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency Paper • 2508.18265 • Published 14 days ago • 182
HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges Paper • 2506.15196 • Published Jun 18 • 3