直播数字人背后：小模型靠“换装训练”追上大模型
直播间的数字人主播要一边卖货一边答问题，还得随时换话术、换活动规则。大模型聪明但反应慢，小模型快但一换规则就懵。这篇来自淘宝直播的技术报告，核心是让紧凑模型学会“适应变化”：训练时故意把提示词、工具接口、技能名称都打乱重排，让模型在千变万化的配置里练出稳定能力。结果在直播问答上拿到94.8分，超过最强通用大模型的93.0，延迟还压在3.4秒。它不是你明天能直接用的东西，但它说明一个趋势：AI落地的瓶颈不在模型大小，而在模型能不能跟上业务改版的速度。
📄 原文摘要(英文)
AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates, and accurate yet effective responses. Evolvable Harnesses, whose Skills, Hooks, prompts, and tools can be updated independently of model weights, enable rapid iteration but expose a trade-off: large models adapt zero-shot yet are too slow, whereas compact models meet latency targets but overfit to fixed Harness configurations. We propose Harness-Aware Training (HAT), which trains compact models to adapt to changing Harnesses. Its key component, Harness-State Augmentation (HSA), applies task-preserving transformations to Skill identifiers and content, tool schemas, prompt structures, and Hook functions. Training proceeds in three stages: HSA-SFT learns reasoning and tool use from strong-model trajectories across diverse environments; General On-Policy Distillation restores generalization lost during SFT; and HSA-RL improves robustness to changing Harnesses through reinforcement learning in augmented environments. Across four evaluation sets, HAT achieves 94.8 on Live-Stream QA (base: 80.3; strongest general LLM: 93.0) and 94.6 on Harness-Variant QA (base: 75.4). Unlike Fixed-Harness SFT, which lowers IFEval by 7.7 points from the base model, HAT avoids this regression and reaches 83.5. On one NVIDIA H20 GPU, the optimized system delivers P50 and P95 latencies of 3.4 s and 8.1 s. Deployed in Taobao Live's digital-avatar service, it also yields positive online A/B test results for GMV and item-page views.