홈 › Papers

Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report

2026-08-22 · TaoLive AIGC LLM Team, Yuhan Sun, Wenhao Lin, Yongdong Luo, Yibo Hu, Meiguang Jin, Junfeng Ma, Weihang Pan, Jiaxin Zhao, Zulong Chen hf

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.

📄 PDF Abstract BibTeX arXiv:2608.15763

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

2026-05-21 · Tianshi Xu, Huifeng Wen, Meng Li arxiv

LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adapta…

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

2026-05-28 · Minhua Lin, Juncheng Wu, Zijun Wang, Zhan Shi 외 arxiv

LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution…

Instruction Following

DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations

2026-05-23 · Lirong Che, Yuzhe yang, Peiwen lin, Chuang wang 외 arxiv

Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptation: instead of updating model weights, a…

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

2026-09-15 · Shuhan Xue, Jianyuan Zhong, Ziyuan Nan, Wenbin Li 외 arxiv

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying …

Reinforcement Learning Continual Learning

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

2026-06-01 · Zewen Liu, Zhan Shi, Yisi Sang, Bing He 외 arxiv

Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on …