# Intent-Driven LLM Ensemble Planning for Flexible Multi-Robot Disassembly: Demonstration on EV Batteries

arXiv: https://arxiv.org/abs/2510.17576 · HTML: https://mlsanity.com/paper/2510.17576/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Mixture-of-Depths: Dynamically allocating compute in transformer-based language models](https://mlsanity.com/paper/2404.02258/) (2024)
- [ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2312.16217/) (2023)
- [FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models](https://mlsanity.com/paper/2310.20410/) (2023)
- [Understanding Large-Language Model (LLM)-powered Human-Robot Interaction](https://mlsanity.com/paper/2401.03217/) (2024)
- [Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy](https://mlsanity.com/paper/2410.01345/) (2024)
- [Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration](https://mlsanity.com/paper/2406.14097/) (2024)
- [M-IFEval: Multilingual Instruction-Following Evaluation](https://mlsanity.com/paper/2502.04688/) (2025)
- [RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models](https://mlsanity.com/paper/2310.10221/) (2023)
- [Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration](https://mlsanity.com/paper/1802.01780/) (2018)
- [Mixed-Initiative variable autonomy for remotely operated mobile robots](https://mlsanity.com/paper/1911.04848/) (2019)
- [A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation](https://mlsanity.com/paper/2109.12045/) (2021)
- [Exploring Large Language Models to Facilitate Variable Autonomy for Human-Robot Teaming](https://mlsanity.com/paper/2312.07214/) (2023)
- [A Supervised Machine Learning Approach to Operator Intent Recognition for Teleoperated Mobile Robot Navigation](https://mlsanity.com/paper/2304.14003/) (2023)
- [A Mini-Review on Mobile Manipulators with Variable Autonomy](https://mlsanity.com/paper/2408.10887/) (2024)
- [Toward Zero-Shot User Intent Recognition in Shared Autonomy](https://mlsanity.com/paper/2501.08389/) (2025)
- [Probabilistic Human Intent Prediction for Mobile Manipulation: An Evaluation with Human-Inspired Constraints](https://mlsanity.com/paper/2507.10131/) (2025)
- [An Intent-based Task-aware Shared Control Framework for Intuitive Hands Free Telemanipulation](https://mlsanity.com/paper/2003.03677/) (2020)
- [Adaptive Task Allocation in Multi-Human Multi-Robot Teams under Team Heterogeneity and Dynamic Information Uncertainty](https://mlsanity.com/paper/2409.13824/) (2024)
- [Hybrid Task and Motion Planning with Reactive Collision Handling for Multi-Robot Disassembly of Complex Products: Application to EV Batteries](https://mlsanity.com/paper/2509.21020/) (2025)

## Abstract (arXiv)

This paper addresses the problem of planning complex manipulation tasks, in which multiple robots with different end-effectors and capabilities, informed by computer vision, must plan and execute concatenated sequences of actions on a variety of objects that can appear in arbitrary positions and configurations in unstructured scenes. We propose an intent-driven planning pipeline which can robustly construct such action sequences with varying degrees of supervisory input from a human using simple language instructions. The pipeline integrates: (i) perception-to-text scene encoding, (ii) an ensemble of large language models (LLMs) that generate candidate removal sequences based on the operator's intent, (iii) an LLM-based verifier that enforces formatting and precedence constraints, and (iv) a deterministic consistency filter that rejects hallucinated objects. The pipeline is evaluated on an example task in which two robot arms work collaboratively to dismantle an Electric Vehicle battery for recycling applications. A variety of components must be grasped and removed in specific sequences, determined by human instructions and/or by task-order feasibility decisions made by the autonomous system. On 200 real scenes with 600 operator prompts across five component classes, we used metrics of full-sequence correctness and next-task correctness to evaluate and compare five LLM-based planners (including ablation analyses of pipeline components). We also evaluated the LLM-based human interface in terms of time to execution and NASA TLX with human participant experiments. Results indicate that our ensemble-with-verification approach reliably maps operator intent to safe, executable multi-robot plans while maintaining low user effort.