# Adaptive Code Generation for Controlling Robots

arXiv: https://arxiv.org/abs/2610.09588 · HTML: https://mlsanity.com/paper/2610.09588/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 7 of 7)

- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds](https://mlsanity.com/paper/2602.00807/) (2026)
- [Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models](https://mlsanity.com/paper/2412.19450/) (2024)

## Abstract (arXiv)

Deploying robots as Complex Adaptive Systems (CAS) in unknown and dynamic environments necessitates a transition from rigid command libraries toward intention-based autonomy, as natural language represents the only medium capable of articulating complex goals beyond the capacity of finite instruction sets. While Large Language Models (LLMs) offer a path toward natural language goal description, their integration introduces significant challenges: the formalization gap between imprecise intentions and executable actions, the taxonomy gap induced by unpredictable environments, and the challenge of maintaining temporal state and progress awareness. This work introduces an architectural framework that enables robotic control by leveraging generative AI. The system follows a dual-AI design: an LLM translates high-level intentions into executable program code restricted to a formal robotic library and constrained by verifiable syntax, while a Vision-Language Model (VLM) provides semantic grounding via a distillation process. To ensure robustness, the framework incorporates environment-driven replanning triggers based on geometric and semantic thresholds, complemented by continuous runtime monitoring and an adaptive planning loop. Benchmarked across frontier models, our framework architecture demonstrates that grounding generative AI in a reactive, constrained loop enables robust fulfillment of complex intentions in dynamic and unknown environments.