LLM Reasoning 相关度: 9/10

EcoThink: A Green Adaptive Inference Framework for Sustainable and Accessible Agents

Linxiao Li, Zhixiang Lu
arXiv: 2603.25498v1 发布: 2026-03-26 更新: 2026-03-26

AI 摘要

EcoThink提出了一种节能自适应推理框架,降低LLM推理过程中的能源消耗并提升可持续性。

主要贡献

  • 提出EcoThink框架,通过动态评估query复杂度减少不必要的推理
  • 通过知识蒸馏的路由机制,区分简单和复杂query
  • 实验证明EcoThink有效降低推理能耗,最高达81.9%

方法论

采用基于知识蒸馏的轻量级路由机制,动态评估query复杂度,对简单问题跳过不必要的推理过程。

原文摘要

As the Web transitions from static retrieval to generative interaction, the escalating environmental footprint of Large Language Models (LLMs) presents a critical sustainability challenge. Current paradigms indiscriminately apply computation-intensive strategies like Chain-of-Thought (CoT) to billions of daily queries, causing LLM overthinking, a redundancy that amplifies carbon emissions and operational barriers. This inefficiency directly undermines UN Sustainable Development Goals 13 (Climate Action) and 10 (Reduced Inequalities) by hindering equitable AI access in resource-constrained regions. To address this, we introduce EcoThink, an energy-aware adaptive inference framework designed to reconcile high-performance AI intelligence with environmental responsibility. EcoThink employs a lightweight, distillation-based router to dynamically assess query complexity, skipping unnecessary reasoning for factoid retrieval while reserving deep computation for complex logic. Extensive evaluations across 9 diverse benchmarks demonstrate that EcoThink reduces inference energy by 40.4% on average (up to 81.9% for web knowledge retrieval) without statistically significant performance loss. By mitigating algorithmic waste, EcoThink offers a scalable path toward a sustainable, inclusive, and energy-efficient generative AI Agent.

标签

LLM 节能 自适应推理 知识蒸馏 可持续性

arXiv 分类

cs.AI