{"slug": "swarmresearch-orchestrating-coding-agents-for-open-ended-discovery", "title": "SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery", "summary": "Researchers introduced SwarmResearch, an orchestrator-subagent harness that uses a Shepherd Agent to steer a population of Search Agents operating in separate git branches, preventing convergence on single approaches. On 13/15 open-ended optimization tasks, SwarmResearch outperformed state-of-the-art LLM-guided evolution and multi-agent techniques by enabling higher-level exploration and adaptive parallelism.", "body_md": "arXiv:2607.02807v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/swarmresearch-orchestrating-coding-agents-for-open-ended-discovery", "canonical_source": "https://arxiv.org/abs/2607.02807", "published_at": "2026-07-07 04:00:00+00:00", "updated_at": "2026-07-07 04:03:19.592922+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["SwarmResearch", "Shepherd Agent", "Search Agents", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/swarmresearch-orchestrating-coding-agents-for-open-ended-discovery", "markdown": "https://wpnews.pro/news/swarmresearch-orchestrating-coding-agents-for-open-ended-discovery.md", "text": "https://wpnews.pro/news/swarmresearch-orchestrating-coding-agents-for-open-ended-discovery.txt", "jsonld": "https://wpnews.pro/news/swarmresearch-orchestrating-coding-agents-for-open-ended-discovery.jsonld"}}