评分 6 · 来源：cs.AI updates on arXiv.org · 发布于 2026-04-14
评分依据：Key insight: humans improve through interaction without re-executing MAS, but current multi-agent learning requires re-execution at inference. Addresses fundamental inefficiency.
Interactive Learning for LLM Reasoning
发布
采集
学术前沿 6.0 分
— Key insight: humans improve through interaction without re-executing MAS, but current multi-agent learning requires re-execution at inference. Addresses fundamental inefficiency.