Multi-Agent Collaboration Pays Only on Long-Horizon Tasks With Sparse Dependencies

arXiv 2609.19759·medium signalXBlueskyLinkedInCopy link

arXiv 2609.19759 (17 Sep 2026) maps where multi-agent collaboration beats a single-agent harness and finds the boundary is task structure, not model strength: gains concentrate in long-horizon work with sparse dependencies, while single-agent harnesses stay better on tightly coupled sequential workflows where the collaboration cost is pure context overhead. The proposed SAIGE mechanism models collaboration as a graph that grows on demand, spawning agent instances as nodes and drawing edges from content-based retrieval of semantic dependencies. Its most useful negative result for builders is that enlarging the agent pool or deepening recursion did not reliably improve outcomes.