Hello, I'm

Haotian Xu 许皓天

RL-Infra & RL Algorithms · Agentic-RL

Apodex

1,900+ Citations
16 h-index
18 i10-index
Scroll

About Me

I currently work at Apodex, focusing on RL-Infra and RL algorithm development with a focus on Agentic-RL. I built the RL training system behind apodex-v1.0, Apodex's flagship agentic model — a fully-asynchronous stack (on top of miles) that decouples training from rollout, evaluates without pausing training, and reclaims idle training GPUs for generation via hybrid-colocate. I also built async_openrlhf, an open-source, Ray-based high-performance RLHF framework with a fully-async training/rollout pipeline, extending the widely-adopted OpenRLHF. My research spans LLM reasoning, MCTS, scaling laws for agentic reasoning, and efficient reasoning compression.

Research Interests

RL-Infra Agentic-RL LLM Reasoning MCTS RLHF Scaling Laws NLP LLM Safety

Work Experience

2025.11 – Present

Apodex

RL-Infra & RL Algorithms (Agentic-RL)

2024 – 2025.8

Xiaohongshu (小红书) — HiLab

Math-Reasoning & Agentic-RL

2023

Douyin (抖音 / ByteDance)

AIGC Safety

2018 – 2023

Alibaba (阿里巴巴)

Content Safety, Public Opinion Analysis, Personal Privacy, LLM Safety

Education

2013 – 2016

Tsinghua University (清华大学)

Department of Electronic Engineering

2009 – 2013

UESTC (电子科技大学)

Bachelor's Degree

Featured Work · RL-Infra

apodex-v1.0 · RL Training System

apodex-v1.0 is Apodex's flagship agentic model. My main contribution is its RL training system — a fully-asynchronous, high-throughput Agentic-RL stack built on top of miles that fully decouples training from rollout, evaluates the policy without ever pausing the training loop, and squeezes maximum utilization out of every GPU by letting idle training cards double as rollout engines whenever there is no data left to consume.

Fully-Async Train / Inference Separation

Training workers and rollout engines run on independent loops, communicating only through a shared data buffer and output queue, so neither ever blocks the other. Off-policy staleness is bounded by two-level (cross-group + per-slot) filtering and a configurable staleness threshold, with cooperative-abort weight sync over NCCL between iterations.

Async Evaluation — No Training Stalls

A dedicated eval pool hot-reloads the rolling training checkpoints and evaluates in the background, so evaluation never interrupts the training loop (“training-data roll”). Eval failures are isolated and can never abort training, keeping throughput steady while metrics stream continuously.

Hybrid-Colocate GPU Reclamation

When the buffer has no consumable data, colocated training GPUs onload as generation engines and join the rollout routing pool — then offload again for the optimizer step. Idle training cards become extra rollout throughput, driving near-full cluster utilization with dedicated remote engines handling steady-state generation.

2025 Highlights

Top-venue publications accepted in 2025–2026

arXiv 2026
6 citations

MiroThinker: Towards Heavy-Duty Research Agents via Verification & Model-Context Scaling

MiroMind Team (incl. H Xu)

A family of open research agents (MiroThinker-1.7 & h1) that scale long-horizon, verification-centric reasoning, trained with our fully-asynchronous RL stack.

arXiv 2026
1 citation

Argus: Evidence Assembly for Scalable Deep Research Agents

Z Zhang, L Su, Z Chen, X Lin, H Xu, et al.

An evidence-assembly framework that lets deep-research agents accumulate and verify evidence at scale for reliable long-horizon research.

NeurIPS 2025
58 citations

Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving

X Mai, H Xu, W Wang, Y Zhang, W Zhang

Discovering scaling laws for agentic reinforcement learning where LLMs spontaneously learn to execute code for mathematical reasoning.

ICLR 2026
36 citations

IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling

G Chen, Z Qiao, X Chen, D Yu, H Xu, WX Zhao, R Song, W Yin, H Yin, et al.

Rethinking how to scale agent interactions for long-horizon research tasks.

ICLR 2026
16 citations

GEM: A Gym for Generalist LLMs

Z Liu, A Sims, K Duan, C Chen, S Yu, X Zhou, H Xu, S Xiong, B Liu, C Tan, et al.

A comprehensive gym environment for training and evaluating generalist large language models.

ICLR 2026
21 citations

Search Self-Play: Pushing the Frontier of Agent Capability without Supervision

H Lu, Y Wen, P Cheng, R Ding, J Guo, H Xu, C Wang, H Chen, X Jiang, et al.

A novel self-play framework that advances agent capabilities through search without external supervision.

ICLR 2026
8 citations

Omni-DPO: A Dual-Perspective Paradigm for Dynamic Preference Learning of LLMs

S Peng, W Wang, Z Tian, S Yang, X Wu, H Xu, C Zhang, T Isobe, B Hu, M Zhang

A dual-perspective dynamic preference learning framework that adaptively reweights samples by jointly considering data quality and model performance evolution during training.

IEEE TPAMI 2025
498 citations

From System 1 to System 2: A Survey of Reasoning Large Language Models

D Zhang, ZZ Li, ML Zhang, J Zhang, Z Liu, Y Yao, H Xu, J Zheng, X Chen, et al.

A comprehensive survey of reasoning LLMs, tracing the evolution from fast intuitive (System 1) to slow deliberate (System 2) reasoning paradigms.

EMNLP 2025
375 citations

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

J Hu, X Wu, W Shen, JK Liu, W Wang, S Jiang, H Wang, H Chen, B Chen, H Xu, et al.

A Ray-based open-source framework enabling scalable RLHF training, widely adopted by the research community.

ACL 2024
14 citations

ITD: Large Language Models Can Teach Themselves Induction Through Deduction

W Sun, H Xu, X Yu, P Chen, S He, J Zhao, K Liu

Showing that LLMs can bootstrap inductive reasoning capability through deductive self-teaching.

ACL 2026
9 citations

TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression

ZZ Li, X Liang, Z Tang, L Ji, P Wang, H Xu, H Huang, W Deng, Y Gong, et al.

An efficient method to compress long chain-of-thought reasoning while preserving accuracy.

Selected Publications

Full list on Google Scholar

2026

MiroThinker: Towards Heavy-Duty Research Agents via Verification & Model-Context Scaling

MiroMind Team (incl. H Xu)

arXiv preprint 6 citations
2026

Argus: Evidence Assembly for Scalable Deep Research Agents

Z Zhang, L Su, Z Chen, X Lin, H Xu, et al.

arXiv preprint 1 citation
2026

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning

Z Gao, S Shen, T Chai, W Wang, H Xu, et al.

ECCV 2026
2025

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs

Y Hu, S Kang, H Yang, H Xu, M Zhang

NeurIPS 2025 9 citations
2025

MedKGent: A Large Language Model Agent Framework for Constructing Medical Knowledge Graphs

D Zhang, Z Wang, ZZ Li, Y Yu, H Xu, et al.

arXiv preprint 8 citations
2026

LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs

J Jia, X Wu, C Gao, Z Chen, H Xu, et al.

AAAI 2026
2026

Shuttle Between the Instructions and the Parameters of Large Language Models

W Sun, H Xu, H Liao, X Yu, Z Jiang, et al.

ACL 2026
2025

From System 1 to System 2: A Survey of Reasoning Large Language Models

D Zhang, ZZ Li, ML Zhang, J Zhang, Z Liu, Y Yao, H Xu, et al.

IEEE Transactions on Pattern Analysis and Machine Intelligence 498 citations
2025

Reinforce++: Stabilizing Critic-free Policy Optimization with Global Advantage Normalization

J Hu, JK Liu, H Xu, W Shen

arXiv preprint 444 citations
2025

OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework

J Hu, X Wu, W Shen, JK Liu, W Wang, S Jiang, H Wang, H Chen, B Chen, H Xu, et al.

EMNLP 2025 375 citations
2023

CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility

G Xu, J Liu, M Yan, H Xu, J Si, Z Zhou, P Yi, X Gao, J Sang, R Zhang, et al.

arXiv preprint 104 citations
2025

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

H Xu, X Wu, W Wang, Z Li, D Zheng, B Chen, Y Hu, S Kang, J Ji, Y Zhang, et al.

arXiv preprint 69 citations
2024

Interpretable Contrastive Monte Carlo Tree Search Reasoning

Z Gao, B Niu, X He, H Xu, H Liu, A Liu, X Hu, L Wen

arXiv preprint 59 citations
2025

Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving

X Mai, H Xu, W Wang, Y Zhang, W Zhang

NeurIPS 2025 58 citations
2025

Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models

W Sun, X Yu, Z Huang, H Xu, S He, J Zhao, K Liu

CCL 2025 32 citations
2023

No Train Still Gain. Unleash Mathematical Reasoning of LLMs with Monte Carlo Tree Search Guided by Energy Function

H Xu

arXiv preprint 26 citations
2022

Generating Disentangled Arguments with Prompts: A Simple Event Extraction Framework that Works

J Si, X Peng, C Li, H Xu, J Li

ICASSP 2022 22 citations
2026

IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling

G Chen, Z Qiao, X Chen, D Yu, H Xu, WX Zhao, R Song, W Yin, H Yin, et al.

ICLR 2026 36 citations
2024

ITD: Large Language Models Can Teach Themselves Induction Through Deduction

W Sun, H Xu, X Yu, P Chen, S He, J Zhao, K Liu

ACL 2024 14 citations
2026

GEM: A Gym for Generalist LLMs

Z Liu, A Sims, K Duan, C Chen, S Yu, X Zhou, H Xu, S Xiong, B Liu, C Tan, et al.

ICLR 2026 16 citations
2026

Search Self-Play: Pushing the Frontier of Agent Capability without Supervision

H Lu, Y Wen, P Cheng, R Ding, J Guo, H Xu, C Wang, H Chen, X Jiang, et al.

ICLR 2026 21 citations
2026

Omni-DPO: A Dual-Perspective Paradigm for Dynamic Preference Learning of LLMs

S Peng, W Wang, Z Tian, S Yang, X Wu, H Xu, C Zhang, T Isobe, B Hu, M Zhang

ICLR 2026 8 citations
2025

Probabilistic Uncertain Reward Model

W Sun, X Cheng, X Yu, H Xu, Z Yang, S He, J Zhao, K Liu

arXiv preprint 12 citations
2026

TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression

ZZ Li, X Liang, Z Tang, L Ji, P Wang, H Xu, et al.

ACL 2026 9 citations
2020

End-to-end Latent-variable Task-oriented Dialogue System with Exact Log-likelihood Optimization

H Xu, H Peng, H Xie, E Cambria, L Zhou, W Zheng

World Wide Web 23(3) 45 citations

Zhihu Contributions

Technical writing on LLM reasoning, MCTS, and reinforcement learning

haotian

Research interests: Probabilistic Graphical Models, Reinforcement Learning, NLP

485+ Upvotes 8+ Answers
Visit my Zhihu Profile

Get in Touch