用动态拓扑重构让小模型高效完成复杂推理，媲美大模型。
DynaGraph: Lightweight Multi-Model Interaction Framework via Dynamic Topological Reconfiguration
- 通过时分复用微调适配器，在单张消费级显卡上运行多模型。
- 80亿参数模型在策略问答上达到720亿模型的87.6%表现。
- 自动修复局部错误与严重逻辑断裂，降低延迟和令牌消耗超68%。
解决复杂推理任务通常依赖庞大的单体大语言模型，但存在严重计算冗余。虽然通过结构化流水线或多智能体协作可作为替代方案，却面临根本困境：预设静态拓扑易引发级联错误，而无约束动态代理则导致轨迹发散与不可预测的内存膨胀。为此，我们提出DynaGraph，一种基于动态拓扑重构的轻量级多模型框架。执行层面，DynaGraph在共享基座模型上时分复用PEFT适配器，支持全系统训练与推理部署于单张消费级GPU。路由层面，评估器持续监控执行置信度，触发分层自愈机制：细粒度修补用于局部数据缺口，子图重构用于严重逻辑断裂。在StrategyQA、MATH和FinQA上的实验表明，我们的80亿参数模型在策略问答上达到720亿单体模型的87.6%，在MATH上达82.7%。相较无约束动态架构，延迟降低最高达68.1%，令牌消耗减少68.6%。
原文摘要 · Abstract (English)
Tackling complex reasoning tasks typically relies on massive monolithic LLMs, which suffer from severe computational redundancy. While task decomposition through structured pipelines or multi-agent collaborations offers an alternative, these approaches inevitably fall into a critical dilemma: predefined static topologies are highly vulnerable to cascading errors, whereas unconstrained dynamic agents suffer from trajectory divergence and unpredictable memory bloat. To address this, we present DynaGraph, a lightweight multi-model framework driven by dynamic topological reconfiguration. At the execution level, DynaGraph multiplexes time-division PEFT adapters over a shared base model, enabling both full system training and inference deployment on a single consumer-grade GPU. At the routing level, the Evaluator continuously monitors execution confidence to trigger hierarchical self-healing: Fine-grained Patching for localized data gaps and Subgraph Reconstruction for severe logical ruptures. Experiments on StrategyQA, MATH, and FinQA demonstrate our 8B model closely approximates the reasoning capabilities of a 72B monolithic model (e.g., 87.6% on StrategyQA, 82.7% on MATH). Furthermore, it reduces latency by up to 68.1% and token consumption by 68.6% compared to unconstrained dynamic architectures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。