Unleashing the Power of Tree-of-Thoughts for Edge-Enabled AIGC Service Provisioning

2026-05-18

AI Summary

This work addresses the challenge of balancing high latency and output quality when deploying Tree-of-Thoughts (ToT) reasoning on resource-constrained edge devices, where repeated large model invocations incur significant delays. Focusing on creative writing as a case study, the authors formulate ToT as a directed acyclic graph (DAG) and introduce a novel diffusion-based Soft Actor-Critic (DSAC) algorithm by integrating diffusion models into a reinforcement learning framework. DSAC optimizes the allocation of computational "thoughts" under user-specified quality constraints to minimize generation latency. Experimental results demonstrate that DSAC reduces total latency by 8.32%, 11.57%, and 36.09% compared to PPO, SAC, and DDQN, respectively. Notably, even under stringent quality requirements, DSAC achieves over 80% latency reduction relative to purely local generation.

Abstract

Delivering AI-generated content (AIGC) services fundamentally relies on the reasoning capabilities of generative AI (GenAI) models. Chain-of-Thought (CoT) enhances such reasoning by guiding models through intermediate steps, while Tree-of-Thoughts (ToT) further extends CoT by exploring multiple candidate reasoning paths simultaneously, thereby greatly improving AIGC service quality. However, generating diverse reasoning paths requires separate calls to computationally intensive GenAI models, posing significant challenges for resource constrained user devices. In this paper, we investigate mobile edge computing-enabled AIGC service provisioning with ToT prompting. Specifically, using creative writing AIGC tasks as a case study, we first characterize the number of output tokens as a measure of computational resources in GenAI models and establish its relationship with generation delay and quality through experiments with Qwen 2.5-7B-Instruct. Afterward, we introduce a directed acyclic graph (DAG) model to accurately characterize the reasoning process of ToT prompting, where each vertex represents a thought and each directed edge denotes a transition between consecutive thoughts. We then formulate a DAG-based thought assignment problem aimed at minimizing generation delay subject to a user-adjustable quality constraint. To address this problem, we propose a diffusion-based soft actor-critic (DSAC) algorithm that innovatively integrates diffusion models to determine optimal thought assignment decisions. Through extensive simulations, we demonstrate that the proposed DSAC achieves total generation delay reductions of up to 8.32% over PPO, 11.57% over SAC, and 36.09% over DDQN across various simulation settings, while reducing latency by over 80% compared to the fully local generation baseline even under stringent quality requirements.

Problem

• Tree-of-Thoughts
• AIGC
• edge computing
• reasoning paths
• resource constraints

Innovation

• Tree-of-Thoughts
• mobile edge computing
• diffusion-based soft actor-critic
• DAG-based reasoning
• AIGC service provisioning