Hi! I am Zixuan Wang (王子轩), a master's student at Zhejiang University, advised by Prof. Yongliang Shen at REAL Lab. I am also a research intern in the ERNIE Foundation Model team at Baidu, supervised by Tianxiang Sun.

My research focuses on training language agents for complex, long-horizon tasks. I study how interaction feedback and expert experience can provide better learning signals, enabling agents to learn efficiently and generalize to new tasks and environments.

Feel free to reach out at wangzixuan1210@gmail.com.

🐈 Our lab is also recruiting interns — undergraduate and Master’s students are warmly welcomed! See Join.

🔥 News

  • 2026.08 Agent-G² has been accepted to EMNLP 2026 Main!
  • 2026.05 We released BEACON, our ICML 2026 work on milestone-guided learning for long-horizon agents.

📝 Selected Publications

5 papers at top-tier conferences (ICML, ICLR, ACL, EMNLP, ECCV), 2 as (co-)first author. See also my Google Scholar profile. * Equal contribution. Paper Citations246

ICML 2026 BEACON method: milestone trajectory segmentation, temporal reward shaping, and dual-scale advantage estimation

Milestone-Guided Policy Learning for Long-Horizon Language Agents

Zixuan Wang, Yuchen Yan, Hongxing Li, Teng Pan, Dingming Li, Ruiqing Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

BEACON assigns credit to verifiable intermediate progress with milestone-based trajectory segments, temporal reward shaping, and dual-scale advantages.

92.9% success on long-horizon ALFWorld tasks; effective sample utilization improves from 23.7% to 82.0%.

EMNLP 2026 · Main Agent-G² training pipeline with Gaussian guidance and policy optimization

Agent-G²: Gaussian Guidance for Agentic Reinforcement Learning

Zixuan Wang*, Yanrui Miao*, Zhengxi Lu, Teng Pan, Yiwen Qiu, Hongxing Li, Peng Qiu, Ruiqing Zhang, Yongliang Shen

Adaptive Gaussian sampling of expert-trajectory prefixes turns demonstrations into effective exploration guidance, using statistics from existing training rollouts.

95.3% / 98.4% ALFWorld success with Qwen2.5-1.5B / 7B; less than one-third the rollout cost of per-sample probing.

ICLR 2026 · Workshop OmniEAR framework combining environment simulation and embodied reasoning evaluation

OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

Zixuan Wang, Dingming Li, Hongxing Li, Shuo Chen, Yuchen Yan, Wenqi Zhang, Yongliang Shen, Weiming Lu, Jun Xiao, Yueting Zhuang

An automated pipeline synthesizes embodied scenes, tasks, expert trajectories, and task-specific success checks, combining LLM generation with rule-based validation to support agent training and evaluation.

1,500 scenarios across 11 domains, with 16,592 task instances and validated expert demonstrations.

Other Publications (2)

🎓 Background

  • Zhejiang University · Master's student in Artificial Intelligence, 2025–present.
  • Baidu · Research intern with the ERNIE foundation model team, Dec. 2025–present.
  • Henan University · Undergraduate studies in Software Engineering, 2021–2025.

🏅 Honors & Awards

  • 2023 · ICPC Provincial Contest — Gold Medal.
  • 2023 · CCPC Provincial Contest — Gold Medal.
  • 2022 · CCPC Provincial Contest — Gold Medal.
  • Provincial Outstanding Student
  • Provincial Outstanding Graduate

🤝 Service

Reviewer: ACL 2026 · EMNLP 2026 (DocInsights Workshop) · ICLR 2027.