🧑‍🔬 Xichen Zhang

🏛️ Affiliations

🎓Hong Kong University of Science and TechnologyHong Kong · China2026 · 2 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation (2026)
   Training LLM search agents with reinforcement learning creates a trade-off. Live commercial search APIs are realistic but expensive. Offline snapshots such as Wikipedia are cheap, but they often disagree with dataset labels. That mismatch produces faulty rewards, which can punish correct answers or reward lucky…
2. TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization (2026)
   Reinforcement learning for LLM reasoning usually depends on a single correctness signal at the end of a solution.

🤝 Co-authors here

7 co-authors with a page, the most papers together first.

• Haoru Tan ×2
• Jiaya Jia ×2
• Sitong Wu ×2
• Wenhu Zhang ×2
• Bei Yu
• Yinghao Zhu
• Ziyi He

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026 ×2

Updated 2 November 2026

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xichen-zhang/