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

[2608.15763] Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2608.15763 (cs) [Submitted on 16 Aug 2026 ( v1 ), last revised 4 Oct 2026 (this version, v5)] Title: Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report Authors: TaoLive AIGC LLM Team : Yuhan Sun , Wenhao Lin , Yongdong Luo , Yibo Hu , Meiguang Jin , Junfeng Ma , Weihang Pan , Jiaxin Zhao , Zulong Chen View PDF HTML (experimental) Abstract: 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 item-page views. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2608.15763 [cs.CL] (or arXiv:2608.15763v5 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.15763 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yuhan Sun [ view email ] [v1] Sun, 16 Aug 2026 14:32:56 UTC (1,218 KB) [v2] Sat, 22 Aug 2026 04:28:03 UTC (2,509 KB) [v3] Wed, 26 Aug 2026 17:25:18 UTC (2,759 KB) [v4] Fri, 11 Sep 2026 17:18:41 UTC (2,759 KB) [v5] Sun, 4 Oct 2026 15:29:49 UTC (2,761 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report#674531
• RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources#385419
• RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources#321907
• EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?#999873
• Advance Agent#54771