# SOCIA-nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation

arXiv: https://arxiv.org/abs/2505.12006 · HTML: https://mlsanity.com/paper/2505.12006/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 77 references that are in the map.
- First posted on arXiv 17 May 2025.

## 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 30)

- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance](https://mlsanity.com/paper/2401.03729/) (2024)
- [Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation](https://mlsanity.com/paper/2402.14744/) (2024)
- [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024)
- [Automated Unit Test Improvement using Large Language Models at Meta](https://mlsanity.com/paper/2402.09171/) (2024)
- [Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees](https://mlsanity.com/paper/1509.03025/) (2015)
- [How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments](https://mlsanity.com/paper/1806.08295/) (2018)
- [RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought](https://mlsanity.com/paper/2305.11499/) (2023)
- [LLM Harmony: Multi-Agent Communication for Problem Solving](https://mlsanity.com/paper/2401.01312/) (2024)
- [OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents](https://mlsanity.com/paper/2410.21286/) (2024)
- [Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?](https://mlsanity.com/paper/2412.14232/) (2024)
- [RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance](https://mlsanity.com/paper/2410.01242/) (2024)
- [AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms](https://mlsanity.com/paper/2502.18754/) (2025)
- [Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability](https://mlsanity.com/paper/2310.13402/) (2023)
- [Universal Average-Case Optimality of Polyak Momentum](https://mlsanity.com/paper/2002.04664/) (2020)
- [AutoGenesisAgent: Self-Generating Multi-Agent Systems for Complex Tasks](https://mlsanity.com/paper/2404.17017/) (2024)
- [BESSIE: A Behavior and Epidemic Simulator for Use With Synthetic Populations](https://mlsanity.com/paper/2203.11414/) (2022)
- [Human-in-the-Loop Design Cycles -- A Process Framework that Integrates Design Sprints, Agile Processes, and Machine Learning with Humans](https://mlsanity.com/paper/2003.05268/) (2020)
- [Joint Modelling of Cyber Activities and Physical Context to Improve Prediction of Visitor Behaviors](https://mlsanity.com/paper/2008.11400/) (2020)

## Built on by (most cited first, 1 of 1)

- [LangMARL: Natural Language Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2604.00722/) (2026)

## Abstract (arXiv)

In this paper, we present SOCIA-nabla, an end-to-end, agentic framework that treats simulator construction asinstance optimization over code within a textual computation graph. Specialized LLM-driven agents are embedded as graph nodes, and a workflow manager executes a loss-driven loop: code synthesis -> execution -> evaluation -> code repair. The optimizer performs Textual-Gradient Descent (TGD), while human-in-the-loop interaction is reserved for task-spec confirmation, minimizing expert effort and keeping the code itself as the trainable object. Across three CPS tasks, i.e., User Modeling, Mask Adoption, and Personal Mobility, SOCIA-nabla attains state-of-the-art overall accuracy. By unifying multi-agent orchestration with a loss-aligned optimization view, SOCIA-nabla converts brittle prompt pipelines into reproducible, constraint-aware simulator code generation that scales across domains and simulation granularities. We will release the code soon.