# MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition arXiv: https://arxiv.org/abs/2606.00708 ยท HTML: https://mlsanity.com/paper/2606.00708/ ## 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 41 of its 52 references that are in the map. - First posted on arXiv 30 May 2026. ## Placed in - LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/) ## Builds on (most cited first, 30 of 41) - [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023) - [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019) - [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023) - [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022) - [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018) - [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021) - [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016) - [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022) - [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021) - [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022) - [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024) - [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025) - [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023) - [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017) - [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025) - [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024) - [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017) - [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025) - [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024) - [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024) - [Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning](https://mlsanity.com/paper/2007.04074/) (2020) - [A Closer Look at Invalid Action Masking in Policy Gradient Algorithms](https://mlsanity.com/paper/2006.14171/) (2020) - [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020) - [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021) - [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024) - [Quant GANs: Deep Generation of Financial Time Series](https://mlsanity.com/paper/1907.06673/) (2019) - [Sig-Wasserstein GANs for Time Series Generation](https://mlsanity.com/paper/2111.01207/) (2021) - [The Amazon Nova Family of Models: Technical Report and Model Card](https://mlsanity.com/paper/2506.12103/) (2025) ## Built on by (most cited first, 2 of 2) - [OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents](https://mlsanity.com/paper/2606.26350/) (2026) - [EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection](https://mlsanity.com/paper/2608.17933/) (2026) ## Abstract (arXiv) Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, training procedure, evaluation protocol, and refinement strategy for a task. AutoML systems automate parts of this process, but typically search within predefined pipeline, model, and hyperparameter spaces. LLM-based agents offer greater flexibility through retrieval, code generation, and execution feedback, yet their modelling decisions are often unstructured, difficult to verify, and hard to reuse. We introduce textscMOSAIC (Modular Orchestration for Structured Agentic Intelligence and Composition), a structured agentic framework for memory-grounded model selection and workflow construction. Given a task and dataset, textscMOSAIC builds a semantic task profile, retrieves prior cases and source-code modules, and constructs a blueprint: an intermediate representation specifying selected modelling components, composition, interface constraints, and execution requirements. This blueprint turns model selection into a staged, context-grounded search and grounds LLM-based code generation in retrieved evidence rather than unconstrained synthesis. Candidate models are validated by execution and refined using diagnostic feedback, training traces, task metrics, and a failure-aware reinforcement learning policy. We instantiate textscMOSAIC on financial time-series forecasting and generation, where models must satisfy predictive accuracy, distributional fidelity, execution reliability, and downstream financial criteria such as risk and tail behaviour. Experiments against AutoML and agentic baselines show that textscMOSAIC improves task performance, execution success, and decision traceability, demonstrating the value of treating automated data science as structured, reusable, and execution-grounded model selection.