paper-with-me

Papers

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

2025-10-21 · Yuncheng Hua, Sion Weatherhead, Mehdi Jafari, Hao Xue, Flora D. Salim 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.

📄 PDF Abstract BibTeX arXiv:2510.18551

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationCode Repair

Similar Papers 제목 키워드 기반

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

2026-03-05 · Peihao Wang, Ruisi Cai, Zhen Wang, Hongyuan Mei 외 arxiv

Scaling inference-time compute for Large Language Models (LLMs) has unlocked unprecedented reasoning capabilities. However, existing inference-time scaling methods typically rely on inefficient and suboptimal discrete se…

Reinforcement LearningMathematical Reasoning

$\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning

2024-03-21 · Daniel Trippa, Cesare Campagnano, Maria Sofia Bucarelli, Gabriele Tolomei 외

Machine Unlearning, the process of selectively eliminating the influence of certain data examples used during a model's training, has gained significant attention as a means for practitioners to comply with recent data p…

Inference AttackMachine UnlearningMembership Inference Attack

Malliavin Calculus for Score-based Diffusion Models

2025-03-21 · Ehsan Mirafzali, Utkarsh Gupta, Patrick Wyrod, Frank Proske 외

We introduce a new framework based on Malliavin calculus to derive exact analytical expressions for the score function $\nabla \log p_t(x)$, i.e., the gradient of the log-density associated with the solution to stochasti…

Coordinate-wise Armijo's condition

2019-11-18 · Tuyen Trung Truong

Let $z=(x,y)$ be coordinates for the product space $\mathbb{R}^{m_1}\times \mathbb{R}^{m_2}$. Let $f:\mathbb{R}^{m_1}\times \mathbb{R}^{m_2}\rightarrow \mathbb{R}$ be a $C^1$ function, and $\nabla f=(\partial _xf,\partia…

Understanding Gradient Descent on Edge of Stability in Deep Learning

2022-05-19 · Sanjeev Arora, Zhiyuan Li, Abhishek Panigrahi

Deep learning experiments by Cohen et al. [2021] using deterministic Gradient Descent (GD) revealed an Edge of Stability (EoS) phase when learning rate (LR) and sharpness (i.e., the largest eigenvalue of Hessian) no long…

Deep Learning