Ziran Yang I am a first-year Ph.D. student at Electrical and Computer Engineering Department, Princeton University, advised by Prof. Chi Jin. Previously, I did my undergraduate at Yuanpei College, Peking University. I am interested in the intersection of RL and LLMs, especially on certifiable reasoning. Email  /  Google Scholar  /  Github

I view exploration as the core challenge in RL, and test-time search being necessary to achieve it for LLM agents. The key technical problem is how search procedures and expert decision-making systems can be internalized as reasoning ability, rather than remaining external scaffolding. I see two tightly coupled aspects: backfilling expert search behavior into the model through learning, and on-the-fly calibration that lets the model assess uncertainty and decide when to search, explore, or trust its own prediction.

	LeAct: Learning to Reason from Expert Actions Ziran Yang, Chengshuai Shi, Raj Ghugare, Benjamin Eysenbach, Karthik Narasimhan, Chi Jin Under review Distilling certified expert action systems (game solvers, classical planners, theorem provers) into LLM chain-of-thought.
	Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement Jui-Hui Chung, Ziyang Cai, Zihao Li, Qishuo Yin, Rohit Agarwal, Simon Park, Rodrigo Porto, Narutatsu Ri, Ziran Yang, Shange Tang, Xingyu Dang, Hongzhou Lin, Mengdi Wang, Danqi Chen, Chi Jin, Liam H Fowl, Sanjeev Arora AI4MATH@ICML 2026; Arxiv A blueprint-generation and refinement pipeline for efficient Lean theorem proving.
	MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI Bohan Lyu, Yucheng Yang, ..., Ziran Yang, ..., Dawn Song, Chi Jin AI4MATH@ICML 2026; Arxiv A benchmark for evaluating whether AI systems can invent generalizable and scalable ML methods.
	Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning Chengshuai Shi, Wenzhe Li, Xinran Liang, Yizhou Lu, Wenjia Yang, Ruirong Feng, Seth Karten, Ziran Yang, Zihan Ding, Gabriel Sarch, Danqi Chen, Karthik Narasimhan, Chi Jin Preprint, 2026; Arxiv
	Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification Zenan Li*, Ziran Yang*, Deyuan He, Haoyu Zhao, Andrew Zhao, Shange Tang, Kaiyu Yang, Aarti Gupta, Zhendong Su, Chi Jin Project / Paper / Model / Code / X Open SOTA on Lean code verification via hierarchical proof search.
	Goedel-Prover-V2: The Strongest Open-Source Theorem Prover to Date Yong Lin*, Shange Tang*, Bohan Lyu*, Ziran Yang*, Jui-Hui Chung*, Haoyu Zhao*, Lai Jiang*, Yihan Geng*, Jiawei Ge, Jingruo Sun, Jiayun Wu, Jiri Gesi, David Acuna, Kaiyu Yang, Hongzhou Lin*, Yejin Choi, Danqi Chen, Sanjeev Arora, Chi Jin*, AI4MATH@ICML 2025 (Oral), ICLR 2026 Strongest open-source theorem prover to date.
	ALGOVERI: An Aligned Benchmark for Verified Code Generation on Classical Algorithms Haoyu Zhao*, Ziran Yang*, Jiawei Li*, Deyuan He*, Zenan Li*, Chi Jin, Venugopal V. Veeravalli, Aarti Gupta, Sanjeev Arora ICML 2026 (Spotlight); Arxiv
	Understanding the Sources of Uncertainty for Large Language and Multimodal Models Ziran Yang, Shibo Hao, Hao Sun, Lai Jiang, Qiyue Gao, Yian Ma, Zhiting Hu ICLR 2025 Workshop: Quantify Uncertainty and Hallucination in Foundation Models
	From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with Uncertainty-Guided Dropout Decoding Yixiong Fang*, Ziran Yang*, Zhaorun Chen, Zhuokai Zhao, Jiawei Zhou NeurIPS 2025
	Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games Chengdong Ma*, Ziran Yang*, Hai Ci, Jun Gao, Minquan Gao, Xuehai Pan, Yaodong Yang IEEE T-PAMI; Arxiv
	Panacea: Pareto Alignment via Preference Adaptation for LLMs Yifan Zhong*, Chengdong Ma*, Xiaoyuan Zhang*, Ziran Yang, Qingfu Zhang, Siyuan Qi, Yaodong Yang, NeurIPS 2024
	SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset Josef Dai, Tianle Chen, Xuyao Wang, Ziran Yang, Taiye Chen, Jiaming Ji, Yaodong Yang, NeurIPS 2024 (DB Track)
	Offline Reinforcement Learning for LLM Multi-Step Reasoning Huaijie Wang, Shibo Hao, Hanze Dong, Shenao Zhang, Yilin Bao, Ziran Yang, Yi Wu ACL 2025; ICLR 2025 Workshop: Reasoning and Planning for LLMs (Oral)

	ByteDance Seed 2025.05 - 2025.08 Research Intern Working on RL for Tool-using Agentic LLMs.
	UC San Diego 2024.04 - 2024.11 Research Intern Advisor: Prof. Zhiting Hu
	PAIR Lab: PKU Alignment and Interaction Research Lab 2023.05 - Present Research Intern Advisor: Prof. Yaodong Yang