📡 RSS: Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search — arXiv:2606.17209v1 Announce Type: new Abstract: Test-time scaling for agentic search typically increases depth (i.e., more turns and tokens per trajectory) or breadth (i.e., more parallel rollouts). Here we focus on breadth scaling, showing that standard parallel sampling yields diminishing returns

Created: 6/17/2026, 6:02:10 AM · Connections: 0