# FlowPlan: Zero-Shot Task Planning with LLM Flow Engineering for Robotic Instruction Following

arXiv: https://arxiv.org/abs/2503.02698 · HTML: https://mlsanity.com/paper/2503.02698/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2025.

## Built on by (most cited first, 3 of 3)

- [When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution](https://mlsanity.com/paper/2605.14504/) (2026)
- [Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation](https://mlsanity.com/paper/2503.13055/) (2025)
- [HEART: Coordination of Heterogeneous Expert Agents for Physically Grounded Robotic Task Planning](https://mlsanity.com/paper/2606.25404/) (2026)

## Abstract (arXiv)

Robotic instruction following tasks require seamless integration of visual perception, task planning, target localization, and motion execution. However, existing task planning methods for instruction following are either data-driven or underperform in zero-shot scenarios due to difficulties in grounding lengthy instructions into actionable plans under operational constraints. To address this, we propose FlowPlan, a structured multi-stage LLM workflow that elevates zero-shot pipeline and bridges the performance gap between zero-shot and data-driven in-context learning methods. By decomposing the planning process into modular stages--task information retrieval, language-level reasoning, symbolic-level planning, and logical evaluation--FlowPlan generates logically coherent action sequences while adhering to operational constraints and further extracts contextual guidance for precise instance-level target localization. Benchmarked on the ALFRED and validated in real-world applications, our method achieves competitive performance relative to data-driven in-context learning methods and demonstrates adaptability across diverse environments. This work advances zero-shot task planning in robotic systems without reliance on labeled data. Project website: https://instruction-following-project.github.io/.