PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence

arXiv 2605.18067 ↗First posted 18 May 2026cs.CLcited by 3

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Deploying large language model (LLM) on edge device enables personalized LLM agents for various users. The growing availability of diverse personalized agents presents a unique opportunity for peer-to-peer (P2P) collaboration, wherein each user can delegate tasks beyond the local agent's expertise to remote agents more suited for the specific query. This paper introduces PPAI, the first personalized LLM agent interoperability system, which enables users to collaborate with each other based on agent specialization. However, the ever-changing pool of agents and their interchangeable capacity introduce new challenges when it comes to matching queries to agents and balancing loads, compared with existing P2P systems. Therefore, we propose a scalable query-agent pair scoring mechanism based on prototypes to identify suitable agents within a P2P network with churn. Moreover, we propose a multi-agent interoperability Bayesian game to balance local demand and global efficiency, when changes in remote agent load occur too quickly to be observed. Finally, we implement a prototype of PPAI and demonstrate that it substantially broadens the range of tasks that could be carried out while maintaining load balance. On average, it achieves an accuracy improvement of up to 7.96% across multiple tasks, while reducing latency by 16.34% compared to the baseline.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 35 of its 50 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

35 of 50 references.

Closest ancestors · 4

Same direction, newest first

Other references · 31

2022Training language models to follow instructions with human feedbackcited by 15,971
2024The Llama 3 Herd of Modelscited by 14,715
2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
2021Training Verifiers to Solve Math Word Problemscited by 10,109
2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
2020Measuring Massive Multitask Language Understandingcited by 7,963
2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
2017Prototypical Networks for Few-shot Learningcited by 3,015
2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839

19 more

2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
2023TIES-Merging: Resolving Interference When Merging Modelscited by 818
2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 716
2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
2024HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMscited by 265
2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 189
2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 145
2025OpenCodeReasoning: Advancing Data Distillation for Competitive Codingcited by 113
2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 91
2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 88
2023Fusing Models with Complementary Expertisecited by 46
2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
2025Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipelinecited by 21
2025D2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Servingcited by 20
2025MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructionscited by 16
2025Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Managementcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

Similar, not cited

Close in wording, no citation either way