# Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networks

arXiv: https://arxiv.org/abs/2505.06378 · HTML: https://mlsanity.com/paper/2505.06378/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 58 references that are in the map.
- First posted on arXiv 9 May 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

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

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Sionna: An Open-Source Library for Next-Generation Physical Layer Research](https://mlsanity.com/paper/2203.11854/) (2022)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [Embodied Understanding of Driving Scenarios](https://mlsanity.com/paper/2403.04593/) (2024)
- [MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World](https://mlsanity.com/paper/2401.08577/) (2024)
- [PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning](https://mlsanity.com/paper/2001.05012/) (2020)
- [Five Facets of 6G: Research Challenges and Opportunities](https://mlsanity.com/paper/2212.07902/) (2022)
- [Multi-Agent Deep Reinforcement Learning for Dynamic Avatar Migration in AIoT-enabled Vehicular Metaverses with Trajectory Prediction](https://mlsanity.com/paper/2306.14683/) (2023)
- [Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning](https://mlsanity.com/paper/2406.01820/) (2024)
- [Blockchain-assisted Twin Migration for Vehicular Metaverses: A Game Theory Approach](https://mlsanity.com/paper/2309.02173/) (2023)
- [ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models](https://mlsanity.com/paper/2409.00301/) (2024)
- [NTK-Guided Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2403.12486/) (2024)
- [Joint User Association and Resource Pricing for Metaverse: Distributed and Centralized Approaches](https://mlsanity.com/paper/2208.06770/) (2022)
- [Learning-based Incentive Mechanism for Task Freshness-aware Vehicular Twin Migration](https://mlsanity.com/paper/2309.04929/) (2023)
- [When Metaverses Meet Vehicle Road Cooperation: Multi-Agent DRL-Based Stackelberg Game for Vehicular Twins Migration](https://mlsanity.com/paper/2312.17081/) (2023)
- [Tiny Multi-Agent DRL for Twins Migration in UAV Metaverses: A Multi-Leader Multi-Follower Stackelberg Game Approach](https://mlsanity.com/paper/2401.09680/) (2024)
- [PRIMAL: PRofIt Maximization Avatar pLacement for Mobile Edge Computing](https://mlsanity.com/paper/1510.04340/) (2015)
- [Efficient Twin Migration in Vehicular Metaverses: Multi-Agent Split Deep Reinforcement Learning with Spatio-Temporal Trajectory Generation](https://mlsanity.com/paper/2503.23290/) (2025)

## Abstract (arXiv)

With the advancement of large language models and embodied Artificial Intelligence (AI) in the intelligent transportation scenarios, the combination of them in intelligent transportation spawns the Vehicular Embodied AI Network (VEANs). In VEANs, Autonomous Vehicles (AVs) are typical agents whose local advanced AI applications are defined as vehicular embodied AI agents, enabling capabilities such as environment perception and multi-agent collaboration. Due to computation latency and resource constraints, the local AI applications and services running on vehicular embodied AI agents need to be migrated, and subsequently referred to as vehicular embodied AI agent twins, which drive the advancement of vehicular embodied AI networks to offload intensive tasks to Roadside Units (RSUs), mitigating latency problems while maintaining service quality. Recognizing workload imbalance among RSUs in traditional approaches, we model AV-RSU interactions as a Stackelberg game to optimize bandwidth resource allocation for efficient migration. A Tiny Multi-Agent Bidirectional LSTM Proximal Policy Optimization (TMABLPPO) algorithm is designed to approximate the Stackelberg equilibrium through decentralized coordination. Furthermore, a personalized neural network pruning algorithm based on Path eXclusion (PX) dynamically adapts to heterogeneous AV computation capabilities by identifying task-critical parameters in trained models, reducing model complexity with less performance degradation. Experimental validation confirms the algorithm's effectiveness in balancing system load and minimizing delays, demonstrating significant improvements in vehicular embodied AI agent deployment.