Tianshuo
Peng

I am a PhD student at MMLab, The Chinese University of Hong Kong, supervised by Prof. Xiangyu Yue. I received my bachelor's degree from Wuhan University, advised by Prof. Zuchao Li and Prof. Lefei Zhang.

I am a core member of the InternAgent team at Shanghai AI Laboratory, working closely with Dr. Bo Zhang. My work focuses on leading large-scale mid-training for fundamental agent capabilities, and developing long-horizon deep research tasks.

My research focuses on agentic models that can execute complex long-horizon tasks in real-world scenarios. I am interested in building systems with strong reasoning and execution capabilities through scaling model-environment interaction. In addition, I am broadly interested in multimodal reasoning, vision-language representation learning, and unified multimodal models.

I am always open to potential discussions and collaborations. Please feel free to reach out by email if you are interested in my work or would like to explore possible collaborations.

Tianshuo Peng 22.3N 114.2E ID:2025-X
SYS.ACTIVE / MMLAB-HK / 2026

Research Interests

Agentic Foundation Models

Long-horizon task execution, deep research, scientific discovery, model-environment interaction

Thinking & Interaction Patterns

Novel thinking and interaction patterns for enhanced logical reasoning and planning capabilities

Multimodal Models & Representation

Multimodal reasoning, unified multimodal models, vision-language representation

News

Selected Publications

arXiv 2026
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
InternAgent Team, Shanghai AI Laboratory
arXiv preprint, 2026
arXiv 2026
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Intern-S1-Pro Team, Shanghai AI Laboratory
arXiv preprint, 2026
ICML 2026
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
Jiakang Yuan*, Tianshuo Peng*, Yilei Jiang, Yiting Lu, Renrui Zhang, Kaituo Feng, Chaoyou Fu, Tao Chen, Lei Bai, Bo Zhang, Xiangyu Yue (*Equal contribution)
Forty-Third International Conference on Machine Learning (ICML), 2026
ACL Findings 2026
Exploring Reasoning Reward Model for Agents
Kaixuan Fan, Kaituo Feng, Manyuan Zhang, Tianshuo Peng, Zhixun Li, Yilei Jiang, Shuang Chen, Peng Pei, Xunliang Cai, Xiangyu Yue
Findings of the Association for Computational Linguistics: ACL 2026
arXiv 2025
InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
InternAgent Team, Shanghai AI Laboratory
arXiv preprint, 2025
NeurIPS 2025
Video-R1: Reinforcing Video Reasoning in MLLMs
Kaituo Feng, Kaixiong Gong, Bohao Li, Zonghao Guo, Yibing Wang, Tianshuo Peng, Junfei Wu, Xiaoying Zhang, Benyou Wang, Xiangyu Yue
Advances in Neural Information Processing Systems (NeurIPS), 2025
ICCV 2025
Chimera: Improving Generalist Model with Domain-Specific Experts
Tianshuo Peng, Mingsheng Li, Jiakang Yuan, Hongbin Zhou, Renqiu Xia, Renrui Zhang, Lei Bai, Song Mao, Bin Wang, Aojun Zhou, Botian Shi, Tao Chen, Bo Zhang, Xiangyu Yue
International Conference on Computer Vision (ICCV), 2025
ACM MM 2024
Multi-modal Auto-regressive Modeling via Visual Tokens
Tianshuo Peng, Zuchao Li, Lefei Zhang, Hai Zhao, Ping Wang, Bo Du
ACM Multimedia (MM), 2024
AAAI 2024
A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis
Tianshuo Peng, Zuchao Li, Ping Wang, Lefei Zhang, Hai Zhao
The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024
ACL 2023
FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction
Tianshuo Peng, Zuchao Li, Lefei Zhang, Bo Du, Hai Zhao
The 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023

Selected Awards

Invited Talks