# Achieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLM

arXiv: https://arxiv.org/abs/2505.08492 · HTML: https://mlsanity.com/paper/2505.08492/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning](https://mlsanity.com/paper/1802.08705/) (2018)
- [CoPAL: Corrective Planning of Robot Actions with Large Language Models](https://mlsanity.com/paper/2310.07263/) (2023)
- [On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)](https://mlsanity.com/paper/2401.02500/) (2024)
- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [Neuro-Symbolic Procedural Planning with Commonsense Prompting](https://mlsanity.com/paper/2206.02928/) (2022)
- [Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds](https://mlsanity.com/paper/2305.17590/) (2023)
- [A Hierarchical Architecture for Human-Robot Cooperation Processes](https://mlsanity.com/paper/2009.02807/) (2020)
- [A Framework for Neurosymbolic Robot Action Planning using Large Language Models](https://mlsanity.com/paper/2303.00438/) (2023)
- [On the manipulation of articulated objects in human-robot cooperation scenarios](https://mlsanity.com/paper/1801.01757/) (2018)
- [Flexible human-robot cooperation models for assisted shop-floor tasks](https://mlsanity.com/paper/1707.02591/) (2017)
- [End-to-end deep learning-based framework for path planning and collision checking: bin picking application](https://mlsanity.com/paper/2304.00119/) (2023)
- [PDDLFuse: A Tool for Generating Diverse Planning Domains](https://mlsanity.com/paper/2411.19886/) (2024)
- [Deployment and Evaluation of a Flexible Human-Robot Collaboration Model Based on AND/OR Graphs in a Manufacturing Environment](https://mlsanity.com/paper/2007.06720/) (2020)

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

- [On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL](https://mlsanity.com/paper/2601.14456/) (2026)
- [Agentic Neuro-Symbolic Planning and Commissioning for Human-in-the-Loop Industrial Robotics with Digital Twins](https://mlsanity.com/paper/2606.08214/) (2026)

## Abstract (arXiv)

PDDL-based symbolic task planning remains pivotal for robot autonomy yet struggles with dynamic human-robot collaboration due to scalability, re-planning demands, and delayed plan availability. Although a few neurosymbolic frameworks have previously leveraged LLMs such as GPT-3 to address these challenges, reliance on closed-source, remote models with limited context introduced critical constraints: third-party dependency, inconsistent response times, restricted plan length and complexity, and multi-domain scalability issues. We present Gideon, a novel framework that enables the transition to modern, smaller, local LLMs with extended context length. Gideon integrates a novel problem generator to systematically generate large-scale datasets of realistic domain-problem-plan tuples for any domain, and adapts neurosymbolic planning for local LLMs, enabling on-device execution and extended context for multi-domain support. Preliminary experiments in single-domain scenarios performed on Qwen-2.5 1.5B and trained on 8k-32k samples, demonstrate a valid plan percentage of 66.1% (32k model) and show that the figure can be further scaled through additional data. Multi-domain tests on 16k samples yield an even higher 70.6% planning validity rate, proving extensibility across domains and signaling that data variety can have a positive effect on learning efficiency. Although long-horizon planning and reduced model size make Gideon training much less efficient than baseline models based on larger LLMs, the results are still significant considering that the trained model is about 120x smaller than baseline and that significant advantages can be achieved in inference efficiency, scalability, and multi-domain adaptability, all critical factors in human-robot collaboration. Training inefficiency can be mitigated by Gideon's streamlined data generation pipeline.