Chenchen Zhang profile photo

Chenchen Zhang

Senior Researcher, Tencent · Hunyuan Department

I am a Senior Researcher at Tencent Hunyuan and a core contributor to the Hunyuan model family. My work focuses on RL post-training and multi-agent systems for coding, mathematical and scientific reasoning, and long-horizon tasks.

20+ publications at leading AI and NLP conferences, including NeurIPS, ICML, ICLR, ACL, and EMNLP.

Hunyuan · Selected models

Advancing reasoning and agents

Core contributions to the Hunyuan family, with a current focus on RL post-training and multi-agent capabilities.

Hy3

Open-source MoE with stronger reasoning, coding, and agent capabilities.

HY2.0

Post-training for reasoning and instruction following across Think and Instruct.

2024–2025

Earlier Hunyuan models

Foundational work spanning MoE models, reasoning post-training, and adaptive thinking.

Model contributions & technical reports 9 releases

Models & Technical Reports

Hy4

Model Release 2026

Tencent Hy Team

The formal Hy4 release adds visual understanding and computer use, with stronger long-horizon agentic capabilities for coding, research, and real-world workflows.

My role: Core contributor to RL post-training and multi-agent capabilities, with additional contributions to STEM reasoning.

RL post-training Multi-agent Long-horizon agents Multimodal

Hy4 flash

Model Release 2026

Tencent Hy Team

An efficient multimodal model with 12B active parameters and up to 1M-token context, built for everyday agentic workflows. Tencent reports that RL reduces average end-to-end task output tokens by 50%.

My role: Core contributor to RL post-training and multi-agent capabilities.

RL post-training Multi-agent 12B active 1M context

Hy4 preview

Open Model 2026

Tencent Hy Team

Open-source 770B-parameter MoE flagship with 49B active parameters and 1M context, delivering frontier-level performance across coding, productivity, scientific research, and complex agentic tasks.

My role: Core contributor to post-training, reinforcement learning, and agentic capability optimization.

770B MoE 49B active 1M context Agentic Apache 2.0

Hy3

Open Model 2026

Tencent Hunyuan Team

Open-source 295B-parameter MoE model with 21B active parameters and 256K context, built for reasoning, coding, long-context, and agentic workflows.

My role: Core contributor to post-training, RL recipes, and reasoning optimization across STEM and code.

295B MoE 21B active 256K context Apache 2.0

HY2.0

Model Family 2025

Tencent Hunyuan Team

Next-generation Hunyuan model family for reasoning and instruction-following scenarios.

My role: Core contributor to post-training and evaluation for reasoning and instruction-following models.

Reasoning Instruction

Hunyuan-A13B: An Efficient Open-Source MoE Model with 13B Active Parameters

Open Model 2025

Tencent Hunyuan Team

Open-source fine-grained MoE model with 80B total parameters, 13B active parameters, hybrid reasoning, long-context support, and strong agent capabilities.

My role: Core author and contributor to Hunyuan-A13B.

Open-source MoE 13B active Hybrid reasoning Agent capabilities

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought

Tech Report 2025

Tencent Hunyuan Team

My role: Core contributor to reasoning model optimization and adaptive CoT evaluation.

Tech report CoT

Hunyuan-T1

Tech Page 2025

Tencent Hunyuan Team

My role: Core contributor to reasoning post-training, code-reasoning optimization, LiveCodeBench SOTA, and code evaluation.

Reasoning Code reasoning LiveCodeBench SOTA Tech page

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

arXiv 2024

Tencent Hunyuan Team

Open-source MoE LLM with long-context support.

My role: Core contributor to model development and evaluation for the Hunyuan open-source LLM family.

Open-source MoE Long-context

Research

From reasoning to coordinated agents

My research connects RL for reasoning and action with learning to coordinate agent teams, using code and task-level evaluations to measure progress and guide training.

01

RL & Reasoning

Improving code and STEM reasoning through RL post-training, critic feedback, and credit assignment.

02

Multi-Agent Systems

Learning how agent teams delegate, communicate, and coordinate, and how credit should be assigned across their decisions.

03

Code Intelligence & Evaluation

Evaluating how agents build software, use visual feedback, and critique code, then using these insights to guide training and model improvement.

Selected Work

Independent work on multi-agent RL and credit assignment, followed by selected collaborative papers and further research.

Selected research

Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces

arXiv 2026

Chenchen Zhang Single author · Survey & orchestration framework

Develops an orchestration-trace framework for studying how RL can train teams of LLM agents to spawn, delegate, communicate, aggregate results, and stop. Connects reward design with credit assignment across these decisions, identifies gaps in message-level credit and learned stopping, and releases a tagged literature corpus and a replayable trace schema.

Multi-agent RL Orchestration traces Resource hub

From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models

arXiv 2026

Chenchen Zhang Single author · Survey & credit-assignment analysis

Unifies credit assignment across reasoning steps, tool calls, memory operations, and interacting agents. Combines a literature taxonomy with six diagnostics for identifying when credit estimates are meaningful, analyzes the limits of text-only histories, and introduces a CA-ID Card linking causal claims to evidence and falsification tests.

Survey Agentic RL GitHub

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding

ACL 2026

Yuhang Li, Chenchen Zhang, Ruilin Lv, Ao Liu, Ken Deng, Yuanxing Zhang, Jiaheng Liu, Bo Zhou Co-first author

Introduces a vision-grounded RL framework that trains web-coding agents to generate, visually diagnose, and refine interfaces using a multimodal critic. Render-validity rewards and an improvement-only revision rule stabilize learning; a critic-free self-edit cycle retains most of the gains at inference without repeated critic calls.

ACL 2026 Agentic RL Multimodal critic

SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models

ICML 2026

Jingxuan Xu, Ken Deng, Weihao Li, …, Chenchen Zhang, et al. Co-first author

All 38 authors

Jingxuan Xu, Ken Deng, Weihao Li, Songwei Yu, Haoyang Huang, Xinping Lei, Yifan Yao, Huaixi Tang, Zhiyi Lai, Kepeng Lei, Zizheng Zhan, Yanan Wu, Chenchen Zhang, Wenqiang Zhu, Wen Xiang, Zongxian Feng, Han Li, Junqi Xiong, Dailin Li, Zuchen Gao, Kun Wu, Yuanxing Zhang, Wuxuan Gong, Ziyuan Gao, Guanxiang Wang, Yirong Xue, Mengfei Xie, Xiaojiang Zhang, Jinghui Wang, Wenhao Zhuang, Zheng Lin, Huiming Wang, Zhaoxiang Zhang, Yuqun Zhang, Haotian Zhang, Ming Sun, Chen Bin, Jiaheng Liu

Builds a unified benchmark of 2,000 real pull-request tasks spanning eight task types, eight programming scenarios, and ten languages. Evaluations with SWE-Agent and Claude Code expose distinct weaknesses across tasks and languages, connecting agentic coding assessment to the breadth of real developer workflows.

ICML 2026 Agentic coding

ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation

EMNLP 2026

Chenchen Zhang, Yuhang Li, Jiaheng Liu, et al. First author

All 20 authors

Chenchen Zhang, Yuhang Li, Jiaheng Liu, Can Xu, Ao Liu, Changzhi Zhou, Ken Deng, Dengpeng Wu, Guanhua Huang, Kejiao Li, Qi Yi, Ruilin Lv, Shihui Hu, Yue Zhang, Yuhao Jiang, Zenan Xu, Yuanxing Zhang, Wiggin Zhou, Bo Zhou, Fengzong Lian

Introduces automated evaluation of executable visual artifacts using screenshots captured before, during, and after interaction, together with code and task-specific checklists. Across 1,825 tasks in nine domains, the framework measures visual quality and behavior; an expert study reports 90.95% pairwise agreement between the multimodal referee and human judgments.

Code evaluation Multimodal

WebCompass: Evaluating Multimodal Code Agents in Web Development from Vision, Instruction, and Interaction to Implementation

EMNLP 2026

Xinping Lei, Xinyu Che, Junqi Xiong, Chenchen Zhang, et al. Co-first author

All 17 authors

Xinping Lei, Xinyu Che, Junqi Xiong, Chenchen Zhang, Yukai Huang, Chenyu Zhou, Haoyang Huang, Minghao Liu, Letian Zhu, Hongyi Ye, Ken Deng, Zizheng Zhan, Han Li, Yifan Yao, Ming Sun, Zhaoxiang Zhang, Jiaheng Liu

Evaluates web agents across generation, editing, and repair from text, images, and video. Combines checklist-based patch assessment with an Agent-as-a-Judge that runs websites in a browser and creates targeted tests, revealing gaps in visual quality, interaction, and codebase-level reasoning that static code metrics miss.

Web coding Multimodal eval

CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models

arXiv 2025

Chenchen Zhang, Marcus Dong, Jiaheng Liu, et al. First author

All 18 authors

Chenchen Zhang, Marcus Dong, Jiaheng Liu, Wei Zhang, Yejie Wang, Jian Yang, Ge Zhang, Tianyu Liu, Zhongyuan Peng, Yingshui Tan, Yuanxing Zhang, Zhexu Wang, Weixun Wang, Yancheng He, Ken Deng, Wangchunshu Zhou, Wenhao Huang, Zhaoxiang Zhang

Introduces a code-critique benchmark covering both code generation and code question answering across difficulty levels. Basic and advanced protocols, including fine-grained checklists, assess the quality of model critiques and constructive feedback, extending evaluation beyond whether a model can generate a correct solution.

Code critique Benchmark

More Code & Agentic Research

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

ICML 2026

Jingzhe Ding, Shengda Long, Changxin Pu, …, Chenchen Zhang, et al.

All 50 authors

Jingzhe Ding, Shengda Long, Changxin Pu, Ge Zhang, Zhou Huan, Hongwan Gao, Xiang Gao, Chao He, Yue Hou, Fei Hu, Zhaojian Li, Weiran Shi, Zaiyuan Wang, Daoguang Zan, Chenchen Zhang, Xiaoxu Zhang, Chen Qizhi, Xianfu Cheng, Bo Deng, Qingshui Gu, Kai Hua, Juntao Lin, Pai Liu, Mingchen Li, Minghao Li, Xuanguang Pan, Zifan Peng, Yujia Qin, Yong Shan, Zhewen Tan, Haoran Wang, Zihan Wang, Weihao Xie, Yishuo Yuan, Jiayu Zhang, Yunfei Zhao, He Zhu, Liya Zhu, Chenyang Zou, Ming Ding, Jianpeng Jiao, Jiaheng Liu, Minghao Liu, Qian Liu, Chongyang Tao, Jian Yang, Tong Yang, Zhaoxiang Zhang, Xinjie Chen, Wenhao Huang

Tests whether coding agents can turn a requirements document and an empty workspace into an installable Python library. Execution-based evaluation exposes premature stopping, inconsistent planning, and fragile cross-file dependencies over long development trajectories.

From Diagrams to Code: Multilingual Programming with Visual Design

ICML 2026

Linzheng Chai, Jian Yang, Shukai Liu, …, Chenchen Zhang, et al.

All 15 authors

Linzheng Chai, Jian Yang, Shukai Liu, Wei Zhang, Liran Wang, Ke Jin, Tao Sun, Congnan Liu, Chenchen Zhang, Hualei Zhu, Jiaheng Liu, Xianjie Wu, Ge Zhang, Tianyu Liu, Zhoujun Li

Combines a 13.1M-sample multilingual multimodal instruction dataset, a trained code model, and a dedicated benchmark to translate visual designs into programs. The resulting 7B model matches much larger models on the reported evaluation.

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

arXiv 2026

Liya Zhu, Jingzhe Ding, Jian Zhang, …, Chenchen Zhang, et al.

All 66 authors

Liya Zhu, Jingzhe Ding, Jian Zhang, Jianbo Xue, Shihao Liang, Ge Zhang, Yi Zhu, Duju Zeng, Xiang Gao, Qingshui Gu, Mailun Gao, Huimin Che, Yan Zhao, Peiheng Zhou, Haojun Wang, Chaobo Xian, Lili Le, Chi Wu, Yiwei Liu, Shengda Long, Jiale Yang, Fangzhi Xu, Sijin Wu, Haodong Duan, Chao He, Zhaojian Li, Minchao Wang, Huan Zhou, Jiani Hou, Chuqian Yu, Weiran Shi, Hongwan Gao, Jiamin Chen, Guanhong Chen, Tingqin Luo, Kaiyuan Zhang, Zhixin Yao, Qing Hua, Yuhao Jiang, Jin Chen, Pu Chen, Zhenyu Hu, Xingyu Li, Zhengxuan Jiang, Meng Cao, Tianfeng Long, Haozhe Wang, Mingzhang Wang, Yichen Zhang, Yiming Dai, Chenchen Zhang, Jiaying Wang, Xinying Liu, Xingzu Liu, Lingling Zhang, Xinjie Chen, Yujia Qin, Wangchunshu Zhou, Zhiyong Wu, Yang Liu, Jiaheng Liu, Lei Zhang, Shen Yan, Wenhao Huang, Zaiyuan Wang, Xiaolong Chang

Evaluates long-horizon GUI agents in specialized professional software. Diagnoses omitted workflow stages, cascading errors, and goal drift, showing why success on short, general-purpose computer tasks does not establish competence on complete professional workflows.

GUI agents Long-horizon evaluation Professional workflows

AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

ICLR 2026

Jason Chou, Ao Liu, Yuchi Deng, …, Chenchen Zhang, et al.

All 16 authors

Jason Chou, Ao Liu, Yuchi Deng, Zhiying Zeng, Tao Zhang, Haotian Zhu, Jianwei Cai, Yue Mao, Chenchen Zhang, Lingyun Tan, Ziyan Xu, Bohui Zhai, Hengyi Liu, Speed Zhu, Wiggin Zhou, Fengzong Lian

Introduces AutoCodeGen, a pipeline that combines LLM-generated inputs, sandbox execution, reverse problem generation, and filtering to construct challenging coding tasks. Releases a benchmark with balanced coverage of 20 languages, alongside verifiable training data and a multilingual sandbox.

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

ACL 2025

Siming Huang, Tianhao Cheng, Jason Klein Liu, …, Chenchen Zhang, et al.

All 26 authors

Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, Yuantao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang

Releases an open code-model training recipe with model weights, reproducible data pipelines, training protocols, and ablations. Identifies the roles of cleaning, deduplication, code-related text, and synthetic data in building competitive code LLMs.

ACL 2025 Open-source Code LLM

RL & Reasoning

CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization

ACL 2026

Zhongyuan Peng, Yifan Yao, Kaijing Ma, …, Chenchen Zhang, et al.

All 19 authors

Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang, Zhouliang Yu, Luming Li, Minghao Liu, Yihang Xia, Jiawei Shen, Yuchen Wu, Yixin Cao, Zhaoxiang Zhang, Wenhao Huang, Jiaheng Liu, Ge Zhang

Trains a critic to judge whether Lean 4 formalizations preserve the meaning of natural-language mathematics. Combines critic-guided RL, a semantic-fidelity benchmark, and a corpus of over 509K problems to improve reliability beyond compilation success.

ACL 2026 Math formalization

Reinforcement Learning on Pre-Training Data

ACL 2026 · SAC Highlight

Siheng Li, Kejiao Li, Zenan Xu, …, Chenchen Zhang, et al.

All 34 authors

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang Xu, Zheng Fang, Shuai Li, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

Derives RL rewards directly from general text through a next-segment reasoning objective, reducing dependence on manually annotated post-training tasks. Demonstrates gains in continual pre-training and a stronger starting point for subsequent RL post-training.

SAC Highlight Paper RLPT

Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning

ACL 2026 · Findings

Ziyuan Nan, Qi Yi, Di Huang, …, Chenchen Zhang, et al.

All 12 authors

Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou

Co-trains parallel reasoning proposers and a central synthesizer under a shared RL reward, explicitly optimizing the information they exchange. On mathematical reasoning benchmarks, the method improves accuracy while reducing latency under matched token budgets.

ACL 2026 Parallel thinking

Foundation, Pretraining & Efficiency

MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series

arXiv 2024

Ge Zhang, Scott Qu, Jiaheng Liu, Chenchen Zhang, et al.

All 45 authors

Ge Zhang, Scott Qu, Jiaheng Liu, Chenchen Zhang, Chenghua Lin, Chou Leuang Yu, Danny Pan, Esther Cheng, Jie Liu, Qunshu Lin, Raven Yuan, Tuney Zheng, Wei Pang, Xinrun Du, Yiming Liang, Yinghao Ma, Yizhi Li, Ziyang Ma, Bill Lin, Emmanouil Benetos, Huan Yang, Junting Zhou, Kaijing Ma, Minghao Liu, Morry Niu, Noah Wang, Quehry Que, Ruibo Liu, Sine Liu, Shawn Guo, Soren Gao, Wangchunshu Zhou, Xinyue Zhang, Yizhi Zhou, Yubo Wang, Yuelin Bai, Yuhan Zhang, Yuxiang Zhang, Zenith Wang, Zhenzhu Yang, Zijian Zhao, Jiajun Zhang, Wanli Ouyang, Wenhao Huang, Wenhu Chen

Releases a bilingual 7B model trained on 4.5T tokens together with the cleaned corpus, data pipeline, checkpoints, and training infrastructure. Makes the full model-building process available for reproducible research in language, reasoning, and code.

DDK: Distilling Domain Knowledge for Efficient Large Language Models

NeurIPS 2024

Jiaheng Liu, Chenchen Zhang, Jinyang Guo, et al. Co-first author

All 16 authors

Jiaheng Liu, Chenchen Zhang, Jinyang Guo, Yuanxing Zhang, Haoran Que, Ken Deng, Zhiqi Bai, Jie Liu, Ge Zhang, Jiakai Wang, Yanan Wu, Congnan Liu, Jiamang Wang, Lin Qu, Wenbo Su, Bo Zheng

Introduces domain-aware knowledge distillation that smoothly adapts the training-data mixture to performance gaps between teacher and student models. Directs learning toward domains where the student needs more help, improving transfer over fixed-mixture distillation and continued pre-training baselines.

NeurIPS 2024 Efficient LLMs

D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models

NeurIPS 2024

Haoran Que, Jiaheng Liu, Ge Zhang, Chenchen Zhang, et al.

All 16 authors

Haoran Que, Jiaheng Liu, Ge Zhang, Chenchen Zhang, Xingwei Qu, Yinghao Ma, Feiyu Duan, Zhiqi Bai, Jiakai Wang, Yuanxing Zhang, Xu Tan, Jie Fu, Jiamang Wang, Lin Qu, Wenbo Su, Bo Zheng

Models how domain-specific continual pre-training performance changes with data mixture, model size, and training volume. Uses small-scale experiments to select mixtures and transfer scaling predictions across domains, reducing the cost of exhaustive training searches.

My contribution: Core author; wrote most of the underlying codebase for domain-specific continual pre-training and scaling-law experiments.

NeurIPS 2024 Core author Scaling law

E2-LLM: Efficient and Extreme Length Extension of Large Language Models

ACL 2024 · Findings

Jiaheng Liu, Zhiqi Bai, Yuanxing Zhang, Chenchen Zhang, et al.

All 14 authors

Jiaheng Liu, Zhiqi Bai, Yuanxing Zhang, Chenchen Zhang, Yu Zhang, Ge Zhang, Jiakai Wang, Haoran Que, Yukang Chen, Wenbo Su, Tiezheng Ge, Jie Fu, Wenhu Chen, Bo Zheng

Extends usable context lengths through a single training run on short sequences. Scale and position augmentations of rotary embeddings improve robustness to longer contexts, avoiding the need to collect long-context training data for each target window.

Multimodal, Evaluation & Surveys

MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

EMNLP 2026

Shilong Li, Xingyuan Bu, Wenjie Wang, …, Chenchen Zhang, et al.

All 25 authors

Shilong Li, Xingyuan Bu, Wenjie Wang, Jiaheng Liu, Jun Dong, Haoyang He, Hao Lu, Haozhe Zhang, Chenchen Jing, Zhen Li, Chuanhao Li, Jiayi Tian, Chenchen Zhang, Tianhao Peng, Yancheng He, Jihao Gu, Hui Huang, Donghao Zhou, Yuanxing Zhang, Jian Yang, Ge Zhang, Wenhao Huang, Zhaoxiang Zhang, Qiangpeng Yang, Shilei Wen

Introduces 400 questions requiring agents to retrieve and combine evidence from web text, images, and video. Verified evidence checklists support analysis of multimodal dependencies and reasoning paths, exposing limitations hidden by text-only browsing evaluations.

Multimodal agents Browsing benchmark Evaluation

JaggedBench: Measuring Reasoning Invariance via Automated Weakness Exploration

EMNLP 2026 · Findings

Donghao Luo, Chenchen Zhang, Siheng Li, et al. Co-first author

All 11 authors

Donghao Luo, Chenchen Zhang, Siheng Li, Zenan Xu, Qi Yi, Boyuqiu, Weikang Wang, Guanhua Huang, Tao Yang, Bo Zhou, Alex Chan

Introduces Automated Weakness Exploration to generate and verify variations near a model’s apparent capability boundary. Evaluates 24 models on 1,142 variants and identifies 18 recurring failure modes, showing how strong aggregate scores can mask brittle reasoning across mathematics, code, science, and knowledge.

Reasoning evaluation Robustness Benchmark

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

ICLR 2026

Caorui Li, Yu Chen, Yiyan Ji, …, Chenchen Zhang, et al.

All 42 authors

Caorui Li, Yu Chen, Yiyan Ji, Jin Xu, Zhenyu Cui, Shihao Li, Yuanxing Zhang, Zhenghao Song, Dingling Zhang, Ying He, Haoxiang Liu, Yuxuan Wang, Qiufeng Wang, Jiafu Tang, Zhenhe Wu, Jiehui Luo, Zhiyu Pan, Weihao Xie, Chenchen Zhang, Zhaohui Wang, Jiayi Tian, Yanghai Wang, Zhe Cao, Minxin Dai, Ke Wang, Runzhe Wen, Yinghao Ma, Yaning Pan, Sungkyun Chang, Termeh Taheri, Haiwen Xia, Christos Plachouras, Emmanouil Benetos, Yizhi Li, Ge Zhang, Jian Yang, Tianhao Peng, Zili Wang, Minghao Liu, Junran Peng, Zhaoxiang Zhang, Jiaheng Liu

Tests joint audio-visual reasoning with 1,000 manually verified questions across 13 task types, supported by step-by-step reasoning annotations. Emphasizes complementary evidence from sound and video to distinguish multimodal understanding from single-modality shortcuts.

MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models

ICLR 2025

Pei Wang, Yanan Wu, Zekun Wang, …, Chenchen Zhang, et al.

All 15 authors

Pei Wang, Yanan Wu, Zekun Wang, Jiaheng Liu, Xiaoshuai Song, Zhongyuan Peng, Ken Deng, Chenchen Zhang, Jiakai Wang, Junran Peng, Ge Zhang, Hangyu Guo, Zhaoxiang Zhang, Wenbo Su, Bo Zheng

Evaluates tool use across five settings, covering single- and multi-turn interaction, one or multiple tools, and out-of-distribution tasks. Uses ground-truth-based metrics without model judges and provides MTU-Instruct data to improve tool-use abilities.

ICLR 2025 Tool use

ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models

ACL 2024 · Findings

Yanan Wu, Jie Liu, Xingyuan Bu, …, Chenchen Zhang, et al.

All 13 authors

Yanan Wu, Jie Liu, Xingyuan Bu, Jiaheng Liu, Zhanhui Zhou, Yuanxing Zhang, Chenchen Zhang, Zhiqi Bai, Haibin Chen, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Bo Zheng

Organizes English and Chinese mathematics problems into a hierarchy of concepts, revealing weaknesses obscured by average benchmark scores. Couples fine-grained diagnosis with targeted fine-tuning to improve underperforming mathematical concepts.

ACL 2024 Math reasoning

GIEBench: Towards Holistic Evaluation of Group Identity-based Empathy for Large Language Models

arXiv 2024

Leyan Wang, Yonggang Jin, Tianhao Shen, …, Chenchen Zhang, et al.

All 12 authors

Leyan Wang, Yonggang Jin, Tianhao Shen, Tianyu Zheng, Xinrun Du, Chenchen Zhang, Wenhao Huang, Jiaheng Liu, Shi Wang, Ge Zhang, Liuyu Xiang, Zhaofeng He

Measures empathy across 97 group identities in 11 dimensions. Distinguishes understanding a group’s perspective from spontaneously responding in alignment with it, revealing uneven behavior across identities and sensitivity to explicit perspective-taking prompts.

A Comprehensive Survey on Long Context Language Modeling

arXiv 2025

Jiaheng Liu, Dawei Zhu, Zhiqi Bai, …, Chenchen Zhang, et al.

All 37 authors

Jiaheng Liu, Dawei Zhu, Zhiqi Bai, Yancheng He, Huanxuan Liao, Haoran Que, Zekun Wang, Chenchen Zhang, Ge Zhang, Jiebin Zhang, Yuanxing Zhang, Zhuo Chen, Hangyu Guo, Shilong Li, Ziqiang Liu, Yong Shan, Yifan Song, Jiayi Tian, Wenhao Wu, Zhejian Zhou, Ruijie Zhu, Junlan Feng, Yang Gao, Shizhu He, Zhoujun Li, Tianyu Liu, Fanyu Meng, Wenbo Su, Yingshui Tan, Zili Wang, Jian Yang, Wei Ye, Bo Zheng, Wangchunshu Zhou, Wenhao Huang, Sujian Li, Zhaoxiang Zhang

Synthesizes long-context research across data, architectures, workflows, training and inference infrastructure, and evaluation. Connects methods for extending context with analyses of whether models reliably use it, alongside a maintained literature repository.

Survey Long-context GitHub

Updates

News

Selected paper releases, conference updates, and open-source project milestones.

  1. Hy4 and Hy4 flash released. Core contributions to RL and multi-agent capabilities, plus STEM reasoning in Hy4.

  2. Hy4 preview released and open-sourced.

  3. Four papers were accepted to EMNLP 2026: ArtifactsBench, WebCompass, and MM-BrowseComp to the Main Conference, and JaggedBench to Findings.

  4. Hy3 formally released and open-sourced.

  5. ICML 2026: SWE-Compass, NL2Repo-Bench, and From Diagrams to Code.

  6. ACL 2026: RLPT was selected as a SAC Highlight Paper; CriticLean, ReLook, and Rhombus were also accepted.

  7. Hy3 Preview open-sourced and reached #1 on OpenRouter daily global API usage.

  8. ICLR 2026: AutoCodeBench and OmniVideoBench.

  9. Core contributor to the HY2.0 model family.

  10. Hunyuan-A13B released and open-sourced.

  11. Hunyuan-TurboS technical report released.

  12. ACL 2025: OpenCoder.

  13. Core contributor to reasoning-focused Hunyuan-T1.

  14. ICLR 2025: MTU-Bench.

  15. Hunyuan-Large weights and technical report released.

  16. NeurIPS 2024: DDK and D-CPT Law.

  17. ACL 2024: E2-LLM and ConceptMath.

Background

Background

Research, AI infrastructure, and engineering roles across large-scale language model systems.

Experience

Tencent

Hunyuan Department · Senior Researcher

Alibaba

Algorithm Engineer · AI Infrastructure & Research, with early work focused on AI infra

Alibaba

Algorithm Engineer Intern · AI Infrastructure & research systems

Baidu

Algorithm Engineer Intern