mlsanityData to 7 Oct 2026

SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery

arXiv 2607.02807 ↗First posted 2 Jul 2026cs.AIcited by 2

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 34 of its 73 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

34 of 73 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization15 Oct
  2. 2025AlphaEvolve: A coding agent for scientific and algorithmic discovery16 Jun
  3. 2024Agentless: Demystifying LLM-based Software Engineering Agents1 Jul

Other references · 31

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2023Let's Verify Step by Stepcited by 3,598
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  5. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  6. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  7. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  8. 2025s1: Simple test-time scalingcited by 1,311
  9. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  10. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  11. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  12. 2015Illuminating search spaces by mapping elitescited by 406
19 more
  1. 2025EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Testcited by 318
  2. 2023Speculative Decoding with Big Little Decodercited by 163
  3. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 162
  4. 2025ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolutioncited by 146
  5. 2026Learning to Discover at Test Timecited by 94
  6. 2024SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengthscited by 73
  7. 2025ThetaEvolve: Test-time Learning on Open Problemscited by 52
  8. 2025FLEX: Continuous Agent Evolution via Forward Learning from Experiencecited by 51
  9. 2025Barbarians at the Gate: How AI is Upending Systems Researchcited by 48
  10. 2025CodeMonkeys: Scaling Test-Time Compute for Software Engineeringcited by 46
  11. 2026AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimizationcited by 46
  12. 2026EvoX: Meta-Evolution for Automated Discoverycited by 45
  13. 2024SAM Decoding: Speculative Decoding via Suffix Automatoncited by 38
  14. 2026CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discoverycited by 38
  15. 2025ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineeringcited by 30
  16. 2026PACEvolve: Enabling Progress-Aware Consistent Evolutioncited by 21
  17. 2026AVO: Agentic Variation Operators for Autonomous Evolutionary Searchcited by 19
  18. 2026Structured Scaling of AI Discovery Across Diverse Scientific Domainscited by 14
  19. 2026Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Dream-RSI: Recursive Self-Improvement through Evolving Worldscited by 9
  2. 2026Component-Aware Feedback for Self-Evolving Programscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents
  2. 2026Evolving Ensemble of Agents
  3. 2026CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery
  4. 2026Effective Harness Engineering for Algorithm Discovery with Coding Agents
  5. 2026What Do Evolutionary Coding Agents Evolve?
  6. 2026OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Heuristic Design
  7. 2026Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
  8. 2026OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime