Know Your Intent: An Autonomous Multi-Perspective LLM Agent Framework for DeFi User Transaction Intent Mining

TL;DR

This paper introduces TIM, a multi-agent LLM framework that accurately infers user transaction intent in DeFi by integrating a taxonomy, dynamic coordination, and multi-modal data analysis, surpassing existing models.

Contribution

The paper presents a novel multi-agent LLM system with a taxonomy and dynamic planning for robust DeFi intent mining, addressing limitations of prior methods.

Findings

TIM outperforms machine learning, single LLM, and single agent baselines.

The framework effectively mitigates LLM hallucinations and improves verifiability.

Analysis of core challenges in DeFi intent inference.

Abstract

As Decentralized Finance (DeFi) develops, understanding user intent behind DeFi transactions is crucial yet challenging due to complex smart contract interactions, multifaceted on-/off-chain factors, and opaque hex logs. Existing methods lack deep semantic insight. To address this, we propose the Transaction Intent Mining (TIM) framework. TIM leverages a DeFi intent taxonomy built on grounded theory and a multi-agent Large Language Model (LLM) system to robustly infer user intents. A Meta-Level Planner dynamically coordinates domain experts to decompose multiple perspective-specific intent analyses into solvable subtasks. Question Solvers handle the tasks with multi-modal on/off-chain data. While a Cognitive Evaluator mitigates LLM hallucinations and ensures verifiability. Experiments show that TIM significantly outperforms machine learning models, single LLMs, and single Agent baselines. We also analyze core challenges in intent inference. This work helps provide a more reliable understanding of user motivations in DeFi, offering context-aware explanations for complex blockchain activity.