SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery
For researchers using LLM-based agents for open-ended discovery, SwarmResearch addresses the problem of premature convergence, enabling more effective exploration.
SwarmResearch introduces an orchestrator-subagent harness that prevents convergence to a single approach in long-running coding agents, achieving better or comparable solutions on 13/15 open-ended optimization tasks compared to state-of-the-art methods.
Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems. However, they tend to converge onto a single high-level approach, then proceed with low-level edits while missing other superior approaches to the problem. We hypothesize two harness-level design choices contribute to this behavior: accumulating context in a single long-running agent and only exposing a single program state to edit. We introduce SwarmResearch, an orchestrator-subagent harness in which a Shepherd Agent uses global context to steer a population of Search Agents, each operating with local context in their respective git branch. On open-ended optimization tasks, SwarmResearch discovers better or comparable solutions to state-of-the-art LLM-guided evolution and multi-agent techniques on 13/15 tasks, driven by higher-level exploration. Compared with fixed scaling of serial and parallel agents, SwarmResearch's orchestrator-guided scaling discovers better-performing solutions by adapting parallelism at different search depths.