mlsanityData to 14 Oct 2026

Test-Driven Agentic Framework for Reliable Robot Controller

arXiv 2603.00455 ↗First posted 28 Feb 2026cs.RO cs.SY eess.SYcited by 0

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

In this work, we present a test-driven, agentic framework for synthesizing a deployable low-level robot controller for navigation tasks. Given a 2D map with an image of an ultrasonic sensor-based robot, or a 3D robotic simulation environment, our framework iteratively refines the generated controller code using diagnostic feedback from structured test suites to achieve task success. We propose a dual-tier repair strategy to refine the generated code that alternates between prompt-level refinement and direct code editing. We evaluate the approach across 2D navigation tasks and 3D navigation in the Webots simulator. Experimental results show that test-driven synthesis substantially improves controller reliability and robustness over one-shot controller generation, especially when the initial prompt is underspecified. The source code and demonstration videos are available at: https://shivanshutripath.github.io/robotic_controller.github.io.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 23 of its 29 references that are in the map. First posted on arXiv 28 Feb 2026.

Builds on

23 of 29 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View12 Jul
  2. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models8 Dec

Other references · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  5. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  6. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
  7. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  8. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 294
  9. 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
  10. 2024Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulationcited by 70
  11. 2024Real-Time Anomaly Detection and Reactive Planning with Large Language Modelscited by 68
  12. 2023LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoningcited by 59
9 more
  1. 2024Driving Everywhere with Large Language Model Policy Adaptationcited by 53
  2. 2024LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planningcited by 45
  3. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makerscited by 42
  4. 2023Deploying and Evaluating LLMs to Program Service Mobile Robotscited by 36
  5. 2023REAL: Resilience and Adaptation using Large Language Models on Autonomous Aerial Robotscited by 19
  6. 2024Verbalized Machine Learning: Revisiting Machine Learning with Language Modelscited by 17
  7. 2024P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Taskcited by 15
  8. 2024Look Further Ahead: Testing the Limits of GPT-4 in Path Planningcited by 7
  9. 2025LLMPC: Large Language Model Predictive Controlcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MANGO: Automated Multi-Agent Test Oracle Generation for Vision-Language-Action Models
  2. 2026Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
  3. 2026SEAR: Self-Evolving Agentic Robotics
  4. 2026BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation
  5. 2026ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling ↗
  6. 2026Beyond Component Testing: Validating Agentic AI Systems
  7. 2025RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies
  8. 2026PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving