# LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning

arXiv: https://arxiv.org/abs/2503.08508 · HTML: https://mlsanity.com/paper/2503.08508/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning](https://mlsanity.com/paper/2311.17842/) (2023)
- [Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V](https://mlsanity.com/paper/2404.10220/) (2024)
- [MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model](https://mlsanity.com/paper/2403.18760/) (2024)
- [DaDu-Corki: Algorithm-Architecture Co-Design for Embodied AI-powered Robotic Manipulation](https://mlsanity.com/paper/2407.04292/) (2024)
- [InteLiPlan: An Interactive Lightweight LLM-Based Planner for Domestic Robot Autonomy](https://mlsanity.com/paper/2409.14506/) (2024)

## Built on by (most cited first, 2 of 2)

- [RoboAgent: Chaining Basic Capabilities for Embodied Task Planning](https://mlsanity.com/paper/2604.07774/) (2026)
- [ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning](https://mlsanity.com/paper/2512.18571/) (2025)

## Abstract (arXiv)

In recent years, lightweight large language models (LLMs) have garnered significant attention in the robotics field due to their low computational resource requirements and suitability for edge deployment. However, in task planning -- particularly for complex tasks that involve dynamic semantic logic reasoning -- lightweight LLMs have underperformed. To address this limitation, we propose a novel task planner, LightPlanner, which enhances the performance of lightweight LLMs in complex task planning by fully leveraging their reasoning capabilities. Unlike conventional planners that use fixed skill templates, LightPlanner controls robot actions via parameterized function calls, dynamically generating parameter values. This approach allows for fine-grained skill control and improves task planning success rates in complex scenarios. Furthermore, we introduce hierarchical deep reasoning. Before generating each action decision step, LightPlanner thoroughly considers three levels: action execution (feedback verification), semantic parsing (goal consistency verification), and parameter generation (parameter validity verification). This ensures the correctness of subsequent action controls. Additionally, we incorporate a memory module to store historical actions, thereby reducing context length and enhancing planning efficiency for long-term tasks. We train the LightPlanner-1.5B model on our LightPlan-40k dataset, which comprises 40,000 action controls across tasks with 2 to 13 action steps. Experiments demonstrate that our model achieves the highest task success rate despite having the smallest number of parameters. In tasks involving spatial semantic reasoning, the success rate exceeds that of ReAct by 14.9 percent. Moreover, we demonstrate LightPlanner's potential to operate on edge devices.