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

arXiv: https://arxiv.org/abs/2510.18551 · HTML: https://mlsanity.com/paper/2510.18551/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 81 references that are in the map.
- First posted on arXiv 21 Oct 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 33)

- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [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)
- [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024)
- [From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future](https://mlsanity.com/paper/2408.02479/) (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)
- [SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users](https://mlsanity.com/paper/2504.10157/) (2025)
- [GenSim: A General Social Simulation Platform with Large Language Model based Agents](https://mlsanity.com/paper/2410.04360/) (2024)
- [RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought](https://mlsanity.com/paper/2305.11499/) (2023)
- [AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation](https://mlsanity.com/paper/2312.13010/) (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)
- [Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data](https://mlsanity.com/paper/2503.20749/) (2025)
- [TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation](https://mlsanity.com/paper/2502.18712/) (2025)
- [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)
- [YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Models](https://mlsanity.com/paper/2505.07581/) (2025)
- [Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows](https://mlsanity.com/paper/2505.04997/) (2025)
- [LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop](https://mlsanity.com/paper/2402.09346/) (2024)
- [G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration](https://mlsanity.com/paper/2506.09272/) (2025)

## 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. This work is under review, and we will release the code soon.