MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning
MAGIC uses dense-reward reinforcement learning to build mixed-granularity multi-agent graphs that beat baselines on eight benchmarks.
The paper introduces MAGIC, a reinforcement-learning method that builds mixed-granularity collaboration graphs for LLM multi-agent systems. It sequentially selects a functional role, instantiates it as a single agent or a reusable group, and connects it to existing units. Potential-based reward shaping supplies intermediate feedback from probe utility and structural signals while preserving the cumulative task reward. The authors say MAGIC outperforms state-of-the-art baselines across eight benchmarks and shows strong inference efficiency.
- MAGIC builds graphs by selecting role, granularity, and connections sequentially.
- Dense rewards use potential-based shaping from utility and structure.
- Authors report gains over state-of-the-art baselines on eight benchmarks.
- The study also reports stronger inference efficiency than prior generators.
From the original article
1 min read at arxiv.orgCollaboration topology shapes both the performance and execution cost of LLM-based multi-agent systems. Because tasks differ in complexity and required capabilities, recent approaches generate task-specific collaboration graphs that specify agent participation and information flow.
By Kairui Yang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.