XS

Xierui Song

0000-0002-4580-1683

cs.CLcs.AIcs.LGcs.CVcs.ROcs.SE

On Valency

published · living versions

W_bhexk7k6·v1 · currentpublished

KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses

with Zhikang Chen, Yueqing Sun, Sen Cui, Ziang Ye +4

1 version

Preprints & journals

9 papers in the corpus · 2023–2026

KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses2610.27417v1 · Zhikang Chen, Yueqing Sun, Sen Cui et al.2026 · 0 citationsarXivon Valency

Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents2610.13058v1 · Ziang Ye, Wentao Shi, Lei Chen et al.2026 · 0 citationsarXiv

RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments2610.10409v1 · Zhiqin Yang, Chenxin Li, Xiaomeng Hu et al.2026 · 0 citationsarXiv

PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins2609.32423v2 · Yaorui Shi, Yuchun Miao, Yuxin Chen et al.2026 · 0 citationsarXiv

Seed-Coder: Let the Code Model Curate Data for Itself2506.03524v2 · ByteDance Seed, Yuyu Zhang, Jing Su et al.2025 · 3 citationsarXiv

Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese2407.01080v2 · Yunqi Xu, Tianchi Cai, Jiyan Jiang et al.2024 · 6 citationsKDD 2024 (oral)

FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering2406.13779v1 · Tianchi Cai, Zhiwen Tan, Xierui Song et al.2024 · 16 citationsKDD 2024

ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference2312.02554v2 · Tianchi Cai, Xierui Song, Jiyan Jiang et al.2023 · 0 citationsarXiv

Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning2309.02669v1 · Tianchi Cai, Jiyan Jiang, Wenpeng Zhang et al.2023 · 18 citationsarXiv

Career total: 10 works. 9 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.