# SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

arXiv: https://arxiv.org/abs/2606.09730 · HTML: https://mlsanity.com/paper/2606.09730/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 57 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025)
- [Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws](https://mlsanity.com/paper/2404.05405/) (2024)
- [DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research](https://mlsanity.com/paper/2511.19399/) (2025)
- [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://mlsanity.com/paper/2605.03546/) (2026)
- [REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents](https://mlsanity.com/paper/2602.14234/) (2026)
- [OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data](https://mlsanity.com/paper/2603.15594/) (2026)
- [Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters](https://mlsanity.com/paper/2602.10604/) (2026)
- [AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration](https://mlsanity.com/paper/2602.03786/) (2026)
- [LongCat-Flash-Thinking-2601 Technical Report](https://mlsanity.com/paper/2601.16725/) (2026)
- [MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification](https://mlsanity.com/paper/2603.15726/) (2026)
- [RepoZero: Can LLMs Generate a Code Repository from Scratch?](https://mlsanity.com/paper/2605.07122/) (2026)
- [LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents](https://mlsanity.com/paper/2605.05191/) (2026)
- [WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2602.04634/) (2026)
- [WideSeek: Advancing Wide Research via Multi-Agent Scaling](https://mlsanity.com/paper/2602.02636/) (2026)

## Built on by (most cited first, 3 of 3)

- [Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?](https://mlsanity.com/paper/2607.07548/) (2026)
- [WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search](https://mlsanity.com/paper/2607.08662/) (2026)
- [Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis](https://mlsanity.com/paper/2607.23524/) (2026)

## Abstract (arXiv)

Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inherently finite. Recent work explores a paradigm where a main agent decomposes tasks and dispatches subtasks to subagents, which execute and return only summarized results, conserving the main agent's context budget. However, performing this well requires delegation intelligence: the ability to decompose complex tasks, determine when and what to delegate, and integrate returned results into the ongoing workflow. Training data for this capability is scarce in naturally occurring text, and to our knowledge, how to synthesize such data and train models to acquire this capability remains largely unexplored in the open-source community. To bridge this gap, we present a preliminary exploration targeting deep research, a representative long-horizon agent task. Specifically, we design a harness that guides the model toward high-quality task decomposition and delegation, while constraining subagents to return results properly to support the main agent's workflow. The harness-guided trajectories naturally encode correct delegation decisions, which we use as supervised fine-tuning data to internalize delegation intelligence into model weights. Our resulting model, SearchSwarm-30B-A3B, achieves 68.1 on BrowseComp and 73.3 on BrowseComp-ZH, the best results among all models of comparable scale. We will release our harness, model weights, and training data to facilitate future research.