Licheng Liu

I’m a final-year Maths student at Imperial College London, and an incoming CS PhD student at the University of Wisconsin–Madison (Sep 2026). I study agentic RL. Previously, I worked on learning theory, with a focus on online selective prediction.

I’m currently with the post-training group at Stepfun. Previously, I was fortunate to do research with two amazing mentors: Prof. Manling Li (Northwestern MLL Lab) and Mingda Qiao (MIT).

I’m always open to collaboration and would love to chat—don’t hesitate to shoot me an email!

News

May 24, 2026	RAGEN-2: Reasoning Collapse in Agentic RL has been accepted to ICML 2026 as an Oral (top 0.7% of 23,918 submissions)! Huge thanks to all collaborators.
Apr 15, 2026	I’ll be joining the University of Wisconsin–Madison as a CS PhD student in Fall 2026, working on LLM post-training. Very excited for the next chapter!
Sep 18, 2025	Our work Online Prediction with Limited Selectivity has been accepted to NeurIPS’25 as a Spotlight (Top 3.5%)! Heartfelt thanks to my mentor Prof. Mingda Qiao for his invaluable guidance and continuous support throughout my research and growth!
Jul 09, 2025	Our work UFO has been accepted to AI4Math@ICML25. Grateful to to all my co-authors!
Mar 19, 2025	I’m excited to share that I’m joining NU MLL Lab 🔬, advised by Prof. Manling Li! I mainly work with Zihan Wang and am grateful for his guidance.

Selected Publications

ICML

RAGEN-2: Reasoning Collapse in Agentic RL

Zihan Wang, Chi Gui, Xing Jin, and 13 more authors

In Forty-Third International Conference on Machine Learning (ICML), 2026

Oral, top 0.7% of 23,918

Abs Bib

@inproceedings{ragen2,
  title = {RAGEN-2: Reasoning Collapse in Agentic RL},
  author = {Wang, Zihan and Gui, Chi and Jin, Xing and Wang, Qineng and Liu, Licheng and Wang, Kangrui and Chen, Shiqi and Li, Linjie and Yang, Zhengyuan and Zhang, Pingyue and Lu, Yiping and Wu, Jiajun and Fei-Fei, Li and Wang, Lijuan and Choi, Yejin and Li, Manling},
  booktitle = {Forty-Third International Conference on Machine Learning (ICML)},
  year = {2026},
  note = {Oral, top 0.7% of 23,918},
}

NeurIPS
Online Prediction with Limited Selectivity

Licheng Liu and Mingda Qiao

In Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025

Spotlight, top 3.2% of 21,575

Abs arXiv Bib

In this paper, we introduce a model of Prediction with Limited Selectivity (PLS) where the forecaster can start the prediction only on a subset of the time horizon. We study the optimal prediction error both on an instance-by-instance basis and via an average-case analysis. We introduce a complexity measure that gives instance-dependent bounds on the optimal error. For a randomly-generated PLS instance, these bounds match with high probability.
@inproceedings{PLS, title = {Online Prediction with Limited Selectivity}, author = {Liu, Licheng and Qiao, Mingda}, booktitle = {Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS)}, year = {2025}, note = {Spotlight, top 3.2% of 21,575}, primaryclass = {cs.LG}, }
arXiv
Let’s Try Again: Eliciting Multi-Turn Reasoning in Language Models via Simplistic Feedback

Licheng Liu, Zihan Wang, Linjie Li, and 5 more authors

2025

Abs arXiv Bib

In this paper, we propose Unary Feedback as Observation (UFO), a simple multi-turn reinforcement learning method that helps large reasoning models reflect on mistakes and improve through minimal feedback like “Let’s try again.” UFO improves multi-turn reasoning accuracy by up to 14% while maintaining single-turn performance, enabling more deliberate and flexible problem solving.
@misc{ufo, title = {Let's Try Again: Eliciting Multi-Turn Reasoning in Language Models via Simplistic Feedback}, author = {Liu, Licheng and Wang, Zihan and Li, Linjie and Xu, Chenwei and Lu, Yiping and Liu, Han and Sil, Avirup and Li, Manling}, year = {2025}, primaryclass = {cs.LG}, }