01
Profile
I drive Agentic AI ecosystem & technology partnerships at NVIDIA — helping partners build, observe, and evaluate agents on NVIDIA's stack. Before that I built and headed LLM teams at Qifu Technology and JF SmartInvest — where financial agents consumed 600B+ tokens — and shipped conversational AI serving 650M+ users globally at Microsoft Xiaoice. Backed by 10+ papers at top NLP venues, 7 granted invention patents, and the CIPS LLM Special Committee.
02
Key Project Achievements
- NVIDIA – Agentic AI PIC In China: PIC of enterprise-grade Agentic AI solutions in China, with partners including Dify, LangChain Community, MemTensor, Oceabase, Red Hat, Nextie, Hand, iSoftStone, and AsiaInfo.
AgentApplication LayerAgent BuildAgent ObservationAgent EvaluationModelModel Layer · FoundationTrainingInferenceRetrieval
- Qifu Technology – QifuGPT-Chat: Delivered product-level financial LLM in collections QifuGPT-Chat (0.6B~14B) with SFT and On-Policy Distillation with 10%+ performance improvements (77% → 89%) vs online baseline.
- JF SmartInvest – FinSphere: Built Meta learning RL-based investment advisory agent FinSphere（九方灵犀） in 2025; surpassed major players (e.g., 60% win rate vs East Money agent（东方财富-妙想）; 65% win rate vs iWencai（同花顺-问财）).
- Microsoft Xiaoice – COMEDY / XiaobingKnows: Built COMEDY from 0→1 in 2023, a memory-enhanced conversational system, co-developed with HKUST(GZ) and launched on the XEVA platform and Xiaoice Island（小冰岛）; Also delivered XiaobingKnows（小冰知道） in 2021, an open-domain QA system using only online search, before ChatGPT's public release.
- Huawei – Auto Assistant: Core member to the delivery of Huawei's first-generation in-car assistant（车载小艺） in 2020, deployed across X-Project (AITO/问界), C-Project (AVATR/阿维塔), and B-Project (BAIC/北汽).
02b
Key Research Achievements
- FinSphere & FinSearch: (IJCAI 2025 Workshop Oral, ACM ICAIF 2025): financial agent (co-developed with HKUST Shijie Han) & financial search agent (co-developed with Johns Hopkins Yiqing Shen).
- COMEDY: (COLING 2025 Oral, Top 5%): Open-domain compressive memory-enhanced long-term conversational system, co-developed with HKUST(GZ) Nuo Chen.
- Orca: (EMNLP 2023): First Chinese conversational MRC dataset.
- Penguin: (EMNLP 2023): Largest Chinese generative MRC dataset.
- LAUG: (ACL 2021): Robustness evaluation for task-oriented dialogue, co-developed with Minlie Huang, Chief Scientist of Lingxin Intelligent (AI Beings).
03
Work Experience
2026.01 → now
2025.09 → 2026.01
2024.07 → 2025.09
JF Smart Invest (9636.HK) — Senior Manager, Head of LLM Team · Advisor: Wenbing Chen, Chairman & CEO2021.07 → 2024.07
2019.07 → 2021.07
Huawei — NLP Engineer · Huawei Assistant · Advisor: Yi Gao, Expert04
Education
2016 → 2019
USTC (985) — M.Eng. in Automation · University of Science and Technology of China · Advisor: Jun Li, Associate Professor
2012 → 2016
DHU (211) — B.Eng. in Automation · Donghua University · Advisor: Wujun Xu, Associate Professor
05
Publications
Yiqing Shen, Jingshu Zhang, Feng Chen, Kaiyuan Yan, Hongguang Li. FinSearch: A Temporal-Aware Search Agent Framework for Real-Time Financial Information Retrieval with LLMs. ACM ICAIF 2025 (ACM International Conference on AI in Finance), Corresponding. [DOI]
Shijie Han, Jinshu Zhang, YiQing Sheng, Kaiyuan Yang, Hongguang Li. FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools. IJCAI 2025 Workshop (International Joint Conference on Artificial Intelligence · FinLLM 2025), Oral, Corresponding. [DOI]
Changhai Zhou, Shijie Han, Lining Yang, Yuhua Zhou, Xu Cheng, Yibin Wang, Hongguang Li. RankAdaptor: Hierarchical Rank Allocation for Efficient Fine-Tuning Pruned LLMs via Performance Model. NAACL 2025 (Findings of the North American Chapter of the Association for Computational Linguistics), 5781-5795, Corresponding. [DOI]
Changhai Zhou, Yuhua Zhou, Yibin Wang, Shijie Han, Qian Qiao, Hongguang Li. QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models. NAACL 2025 (Findings of the North American Chapter of the Association for Computational Linguistics), 4276-4286, Corresponding. [DOI]
Nuo Chen, Hongguang Li, Jianhui Chang, Juhua Huang, Baoyuan Wang, Jia Li. Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations. COLING 2025 (International Conference on Computational Linguistics), 755-773, Oral (Top 5%). [DOI]
Nuo Chen, Hongguang Li, Baoyuan Wang, Jia Li. From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Prompting. ACL 2024 Workshop (Annual Meeting of the Association for Computational Linguistics · NLRSE). [DOI]
Nuo Chen, Hongguang Li, Junqing He, Yinan Bao, Xinshi Lin, Qi Yang, Jianfeng Liu, Ruyi Gan, Jiaxing Zhang, Baoyuan Wang, Jia Li. Orca: A Few-shot Benchmark for Chinese Conversational MRC. EMNLP 2023 (Findings of the Conference on Empirical Methods in Natural Language Processing), 15685-15699. [DOI]
Nuo Chen, Hongguang Li, Yinan Bao, Baoyuan Wang, Jia Li. Natural Response Generation for Chinese Reading Comprehension. EMNLP 2023 (Findings of the Conference on Empirical Methods in Natural Language Processing), 11068-11081. [DOI]
Jiexi Liu, Ryuichi Takanobu, Jiaxin Wen, Dazhen Wan, Hongguang Li, Weiran Nie, Cheng Li, Wei Peng, Minlie Huang. Robustness Testing of Language Understanding in Task-Oriented Dialog. ACL 2021 (Annual Meeting of the Association for Computational Linguistics), 2467-2480. [DOI]
Guangquan Yuan, Jun Li, Hongguang Li, Yi Du, Yong Li, Alan Yu. Label-Embedding-Based Multi-Core Convolution for Text Categorization. ICACI 2020 (International Conference on Advanced Computational Intelligence).
Yang Li, Hongguang Li, Jun Li, Ning Zhang, Guangquan Yuan. A Deep Semantic Matching Network for Answer Selection. CCC 2019 (Chinese Control Conference), 8683-8688.
Hongguang Li, Jun Li, Wei Tian. A Deep Multiple View Sentence Representation Model for Question Answering. 37th CCC 2018 (Chinese Control Conference), 9456-9460.
06
Patents (Authorized) · 发明专利已授权
CN120030278A · 2025
Method and System for Constructing Large Models in the Securities Domain.
CN118153687A · 2024
Memory-Enhanced Response in Dialogue Systems.
CN117290468B · 2024
Intelligent Dialogue Method, Device, and Storage Medium.
CN115617974A · 2023
Dialogue Processing Method, Device, Equipment, and Storage Medium.
CN115062620A · 2022
Semantic Understanding Method and Device.
CN110134964A · 2019
Text Matching Method Based on Hierarchical CNN and Attention.
CN105749438A · 2016
Personal Escape Assistance Device with Embedded Fire Blanket.
07
Academic Service
Journal Reviewer
Knowledge-Based Systems (CAS Tier 1; IF: 8.8)
Journal of Building Engineering (CAS Tier 1; IF: 6.4)
Conference Reviewer
Knowledge-Based Systems (CAS Tier 1; IF: 8.8)
Journal of Building Engineering (CAS Tier 1; IF: 6.4)
Conference Reviewer
EMNLP 2023~2025
AAAI 2024~2025
ARR 2024~2026
ACL 2025~2026
ICLR 2025~2026
MM 2025~2026
NeurIPS 2026
08
Awards
- Shanghai Scholarship (2014) · 上海市奖学金
- Shanghai Outstanding Graduates (2016) · 上海市优秀毕业生
- First Class Scholarship of USTC (2017-2019) · 中国科学技术大学一等奖学金
# last updated: 2026