# ROMA: Recursive Open Meta-Agent Framework for Long-Horizon Multi-Agent Systems

arXiv: https://arxiv.org/abs/2602.01848 · HTML: https://mlsanity.com/paper/2602.01848/

## 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 34 of its 115 references that are in the map.
- First posted on arXiv 2 Feb 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, 30 of 34)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Self-Evaluation Guided Beam Search for Reasoning](https://mlsanity.com/paper/2305.00633/) (2023)
- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12941/) (2024)
- [Recursive Language Models](https://mlsanity.com/paper/2512.24601/) (2025)
- [EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models](https://mlsanity.com/paper/2312.06281/) (2023)
- [SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models](https://mlsanity.com/paper/2506.01062/) (2025)
- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [Retrieval-Augmented Generation with Conflicting Evidence](https://mlsanity.com/paper/2504.13079/) (2025)

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

- [EvoSkill: Automated Skill Discovery for Multi-Agent Systems](https://mlsanity.com/paper/2603.02766/) (2026)
- [JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution](https://mlsanity.com/paper/2608.25593/) (2026)
- [Rethinking Multi-Agent Collaboration: When More Is Less](https://mlsanity.com/paper/2609.19759/) (2026)

## Abstract (arXiv)

Current agentic frameworks underperform on long-horizon tasks. As reasoning depth increases, sequential orchestration becomes brittle, context windows impose hard limits that degrade performance, and opaque execution traces make failures difficult to localize or debug. We introduce ROMA (Recursive Open Meta-Agents), a domain-agnostic framework that addresses these limitations through recursive task decomposition and structured aggregation. ROMA decomposes goals into dependency-aware subtask trees that can be executed in parallel, while aggregation compresses and validates intermediate results to control context growth. Our framework standardizes agent construction around four modular roles --Atomizer (which decides whether a task should be decomposed), Planner, Executor, and Aggregator -- which cleanly separate orchestration from model selection and enable transparent, hierarchical execution traces. This design supports heterogeneous multi-agent systems that mix models and tools according to cost, latency, and capability. To adapt ROMA to specific tasks without fine-tuning, we further introduce GEPA+, an improved Genetic-Pareto prompt proposer that searches over prompts within ROMA's component hierarchy while preserving interface contracts. We show that ROMA, combined with GEPA+, delivers leading system-level performance on reasoning and long-form generation benchmarks. On SEAL-0, which evaluates reasoning over conflicting web evidence, ROMA instantiated with GLM-4.6 improves accuracy by 9.9% over Kimi-Researcher. On EQ-Bench, a long-form writing benchmark, ROMA enables DeepSeek-V3 to match the performance of leading closed-source models such as Claude Sonnet 4.5. Our results demonstrate that recursive, modular agent architectures can scale reasoning depth while remaining interpretable, flexible, and model-agnostic.