ModuLoop : Low-Level Code Generation using Modular Synthesizer and Closed-Loop Debugger for Robotic Control

• URL: http://arxiv.org/abs/2606.03047v1
• Date: Tue, 02 Jun 2026 02:30:19 GMT
• Title: ModuLoop : Low-Level Code Generation using Modular Synthesizer and Closed-Loop Debugger for Robotic Control
• Abstract summary: Large Language Models (LLMs) have demonstrated impressive performance across various domains, including code generation and problem solving.<n>We propose the Closed-Loop Modular Code Synthesizer framework.<n>This framework leverages a pre-trained LLM without any task-specific fine-tuning to perform modular code planning and generation.<n>We apply the proposed framework to the calibration of an RGB-D camera and a robotic arm, validating its effectiveness in real-world settings.
• Score: 5.438998395090549
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated impressive performance across various domains, including code generation and problem solving. However, their application in robotic control, particularly in low-level tasks that require precise manipulation, real-time feedback, and environment-dependent execution, remains limited. To address this challenge, we propose the Closed-Loop Modular Code Synthesizer framework. This framework leverages a pre-trained LLM without any task-specific fine-tuning to perform modular code planning and generation, and iteratively executes the generated code while inserting debugging probes to observe its behavior. This closed-loop structure facilitates systematic debugging and refinement, ultimately producing executable control programs. We apply the proposed framework to the calibration of an RGB-D camera and a robotic arm, validating its effectiveness in real-world settings. Furthermore, through a subsequent pick-and-place task, we demonstrate not only the accuracy of the calibration but also the potential extensibility of the framework. Across both tasks, the framework achieved high execution accuracy and autonomy, illustrating the practicality and scalability of LLM-based robotic control using our framework.

Related papers

• The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis [50.473217152006875]
  MIMIC is a framework that leverages executable code as a rigorous medium for reasoning data synthesis.<n>MIMIC transforms algorithms into verifiable reasoning trajectories through narrative fusion, code-guided test synthesis, and dynamic code instrumentation.<n>Our method significantly elevates accuracy across general reasoning, complex mathematical benchmarks, and fine-grained deterministic tasks.
  arXiv  Detail & Related papers  (2026-09-13T17:04:16Z)
• A Continual Learning Framework for Adaptive Control of Modular Soft Robots [4.374184567811783]
  Soft robots have attracted significant attention in applications such as medical intervention, rehabilitation, and robotic manipulation.<n>MSRs represent an emerging class of robotic systems with highly deformable and reconfigurable structures capable of performing complex tasks.<n>Existing approaches typically require controllers to be retrained from scratch whenever the robot morphology changes.<n>We propose a continual learning inspired control framework capable of incrementally adapting to changes in robot morphology.
  arXiv  Detail & Related papers  (2026-07-07T19:11:07Z)
• Threading Optimization for Vision-Language-Action Model Inference in Low-Cost Smart Agricultural Manipulation [9.383033161646255]
  Real-Time Action Chunking (RTAC) has been proposed to address these bottlenecks.<n>We present a complete system-level implementation of RTAC tailored for a low-cost robotic manipulation system.
  arXiv  Detail & Related papers  (2026-05-31T02:49:50Z)
• Execution-Verified Reinforcement Learning for Optimization Modeling [49.171122807323634]
  Execution-verified learning framework treats a mathematical programming solver as a deterministic, interactive verifier.<n>Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that EVOM matches or outperforms process-supervised SFT.
  arXiv  Detail & Related papers  (2026-04-01T03:39:11Z)
• EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering [55.56674028743782]
  Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time.<n>We present EasySteer, a unified framework for high-performance, LLM steering built on vLLM.
  arXiv  Detail & Related papers  (2025-09-29T17:59:07Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models [81.12673534903979]
  Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools.<n>We propose ToolCoder, a novel framework that reformulates tool learning as a code generation task.
  arXiv  Detail & Related papers  (2025-02-17T03:42:28Z)
• DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution [114.61347672265076]
  Development of MLLMs for real-world robots is challenging due to the typically limited computation and memory capacities available on robotic platforms. We propose a Dynamic Early-Exit Framework for Robotic Vision-Language-Action Model (DeeR) that automatically adjusts the size of the activated MLLM. DeeR demonstrates significant reductions in computational costs of LLM by 5.2-6.5x and GPU memory of LLM by 2-6x without compromising performance.
  arXiv  Detail & Related papers  (2024-11-04T18:26:08Z)
• MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification [15.438969500630677]
  Large Language Models (LLMs) have demonstrated significant potential in code generation.<n>Most current AI-assisted motion control programming efforts focus on PLCs, with little attention given to high-level languages and function libraries.<n>We introduce MCCoder, an LLM-powered system tailored for generating motion control code, integrated with a soft-motion controller.
  arXiv  Detail & Related papers  (2024-10-19T16:46:21Z)
• RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance [0.6062751776009752]
  Large Language Models (LLMs) have shown incredible potential in code generation tasks. LLMs can generate code based on task descriptions, but accuracy remains limited. We introduce a novel architecture of LLM-based agents for code generation and automatic debug: Refinement and Guidance debugger (RGD) RGD decomposes the code generation task into multiple steps, ensuring a clearer workflow and enabling iterative code refinement based on self-reflection and feedback.
  arXiv  Detail & Related papers  (2024-10-02T05:07:02Z)
• Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs [34.16234805577773]
  We introduce ROBO-INSTRUCT, which synthesizes task-specific simulation environments on the fly during program execution.<n>ROBO-INSTRUCT integrates an LLM-aided post-processing procedure to refine instructions for better alignment with robot programs.
  arXiv  Detail & Related papers  (2024-05-30T15:47:54Z)
• Interactive Character Control with Auto-Regressive Motion Diffusion Models [18.727066177880708]
  We propose A-MDM (Auto-regressive Motion Diffusion Model) for real-time motion synthesis. Our conditional diffusion model takes an initial pose as input, and auto-regressively generates successive motion frames conditioned on previous frame. We introduce a suite of techniques for incorporating interactive controls into A-MDM, such as task-oriented sampling, in-painting, and hierarchical reinforcement learning.
  arXiv  Detail & Related papers  (2023-06-01T07:48:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.