Latest Articles

Dive deep into the world of Artificial Intelligence with our curated collection of articles, covering the latest breakthroughs and insights from leading researchers and engineers.

Filtering by tag:

Multi-Agent Reinforcement Learning

(1 article)

March 23, 2026Technology

WideSeek-R1: Width Scaling for Broad Information Seeking with Multi-Agent RL

WideSeek-R1 reframes broad information seeking as an organizational problem, using a lead-agent-subagent MARL system to parallelize search and approach DeepSeek-R1-level performance with a 4B model.

Qing Ke Ai

WideSeek-R1 Multi-Agent Reinforcement Learning width scaling+3 more

50+ LLM & AI Articles | In-Depth Guides & Tutorials - LangCoPilot | LLM Practical Experience Hub