Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

Excerpt

arXiv:2604.11753v3 Announce Type: replace Abstract: We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel and aggregated into a final response. While such scaling has proven effective for chain-of-thought reasoning, agentic tasks pose unique challenges: trajectories are long, multi-turn, and tool-augmented, and outputs are often open-ended. Aggregating only final answers discards rich informa