#MAGIC
2 stories · 0 in 7 days · 0 in 30 days
Stories, products and papers tagged "MAGIC", newest first.
Oct 1
Sep 23
MAGIC Framework Builds Mixed-Granularity Agent Graphs with Dense-Reward RL
The core shift is per-role granularity: instead of committing an entire organization to single agents or fixed groups, MAGIC mixes both within one graph, which cuts execution cost while keeping reusable collaboration patterns. Researchers and engineers designing multi-agent systems can use the dense-reward shaping approach to train topology generators where sparse final-answer rewards stall learning. Compared with representative topology generators evaluated in the paper, it wins across all eight benchmarks tested.