AutoResearch
Closed-loop agents for scientific discovery.
About me
I research and build reliable AI agents that can reason, learn from feedback, and turn research ideas into systems that work in the real world.
At TaoTian Group @ Alibaba, my current work focuses on AI agent research across three core directions: AutoResearch, post-training, and agentic reinforcement learning. I apply these ideas in Xianyu AI systems and am especially interested in closed-loop research agents, stable reasoning objectives, and high-quality data systems for foundation models.
Before Alibaba, I contributed to foundation-model development at Tencent and Baidu. At Tencent, I worked on the Hunyuan Foundation Model, focusing on mathematical and biomedical capability enhancement, pre-training data, multilingual capability improvement, and Yuanbao AI Search. At Baidu, I contributed to multilingual capability enhancement for the ERNIE Bot 5 (EB5) Foundation Model.
Earlier, at the Chinese Academy of Sciences, I conducted research on knowledge graphs and LLM-based security.
I am always happy to connect and collaborate on ambitious research problems. Feel free to reach out by email or visit my Google Scholar.
Current research
I study how agents can research, learn, and act reliably across three core directions, with Xianyu AI as a practical application domain.
Post-Training
Data and alignment for stronger reasoning.
Agentic RL
Reliable reinforcement learning for tool-using agents.
In progress
CVPR Manuscript
Agent Research Survey
Publications & Manuscripts
Submitted
SILICA: Certified Counterfactual Evaluation of Identifiability in Unseen-Language Induction
Evaluates whether an unseen-language task is identifiable by constructing same-state counterfactual queries with provably different correct actions.
In Preparation
When KL Regularization Fails in Online Reasoning RL: A Token-Level Gradient Contract
Frames KL failures as a token-level gradient-contract problem and proposes ZCPO to enforce zero-sum shared-prefix gradients.
Submitted
Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery
Diagnoses calibration imbalance under low-variance rewards and introduces bounded recovery for credible small reward gaps.
In Preparation
ChronoMem: Interpretable Event Memory for LLM-Augmented Time-Series Forecasting
Uses LLMs to structure external events as an interpretable residual memory rather than directly forecasting numerical values.
Preprint
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents
Introduces CICL, a decision-aware context layer that selects evidence by its expected effect on an agent's next action.
Preprint
Optimizing Text Search: A Novel Pattern Matching Algorithm Based on Ukkonen's Approach
Presents a pattern-matching approach based on Ukkonen's construction for efficient text search.
Published
Basket-Enhanced Heterogenous Hypergraph for Price-Sensitive Next Basket Recommendation
Introduces a basket-enhanced heterogeneous hypergraph for price-sensitive next-basket recommendation. arXiv
Patents
- Under ReviewA Multi-Agent and LLM Collaborative Multi-Dimensional Text Quality Scoring System
- GrantedA Generative Large Model Watermarking Tool Based on Probability Perturbation Encryption
- GrantedA Database Drag Behavior Detection Method Based on Time Series
Work experience
Feb 2026 — Present
TaoTian Group @ Alibaba
AI Agent Researcher · P6
AI Agent research spanning General AutoResearch and multimodal quality inspection for Xianyu.
- General AutoResearch — Re-architected the Agent runtime with bounded loop control, stalled-branch rerouting, evidence-driven hypothesis generation, hierarchical memory, and resumable execution traces. The system autonomously performs bad-case diagnosis, candidate generation, and prompt or policy iteration. Across 19 business-task optimization runs, it completed prompt iteration, candidate validation, and migration validation without human intervention within the optimization loop. Across 4 Agent runtimes × 4 model configurations, the selected stack met target on 8 of 9 controlled image-QC tasks, with 279 migration tests passed.
- Xianyu Multimodal Quality Inspection — Built inspection workflows for viewpoint compliance detection, base photo-quality checks, and visible physical-defect detection. An offline acceptance snapshot limited to nine categories and 80 inspection checks reached 97.54% mean Macro-F1. Separately, the current capability supports 30+ product categories at approximately 30K orders per day.
Oct — Dec 2025
Baidu / ERNIE Foundation Model Core Team
Senior Research Scientist · T4+
DAPO-based post-training and alignment for EB5 on PaddlePaddle.
- Scaled multilingual post-training to 260 H800 GPUs across 80+ languages; reached a Text Arena win rate of 86.4% and multilingual average accuracy of 92%, tied global #2 and China #1 on LMArena in Nov 2025.
- Led ten-axis instruction evolution and a best-of self-play plus human N-to-1 data pipeline; achieved a +25.5% win-rate result against EB45T-VL-SFT-v13 and tied #1 on the internal Vision-Arena.
Mar 2025 — Sep 2025
Tencent / Hunyuan Text-to-Text Pipeline Team
Research Scientist · T5
Yuanbao AI Search with NeuroBERT-pro and GATv2Conv.
- Trained on 8 H100 GPUs and deployed on 800 H100 GPUs for about 50B HTML pages/day; extraction reached 65%, classification improved 70% → 80%, and structural accuracy improved 60% → 65%.
- Improved maximum-rectangle precision 83% → 98% and recall +1.5%; HTML pruning raised recall 73.41% → 98.33% with 57.14% compression and reduced pretraining tokens by over 50%.
- Produced approximately 900B multilingual tokens through instruction evolution and data synthesis.
- Developed and maintained STEM main-text extraction operators, completing 135 deliveries and ranking 2nd among 35 contributors in the closed research program.
Feb 2024 — Mar 2025
Tencent / Hunyuan Strategy Group 4
Research Scientist · T5
Mathematical and biomedical capability enhancement, video processing, data recognition, and audio alignment.
- Built a GPT-4o-based agent pipeline with 99% concept-extraction precision and curated 934 high-quality questions; MMLU improved +11.7 and CMMLU improved +10.2.
- Processed a 10-minute 1080p video in about 80 seconds, with capacity of 20,000 video-hours per month.
- Magika exceeded 99% across 116 file types, running at 10 QPS for 800,000 files/day.
- Whisper alignment reached 99% and delivered 20,000+ transcripts, contributing to a patent.
Nov 2023 — Feb 2024
Institute of Information Engineering, Chinese Academy of Sciences
Research Assistant Intern
Fine-tuned LLM approaches for insider-threat detection and structured knowledge-graph construction.
- Worked with OPT-125M, ChatGLM-6B P-tuning, and LLaMA-7B LoRA on CERT 4.2; AUC and Recall were about 0.99, FPR about 0.3%, training time 30% lower, and compute over 50% lower.
- Curated 20,000+ RDF triples with 98% extraction accuracy and precision +43%.
May 2021 — May 2022
Mico World / Yoho Department
Software Engineer
Frontend architecture and production systems for international social products.
- Greedy Lion H5 generated about 20% of company revenue; critical-path optimization improved load speed 3.7×.
- WakaDashboard delivered over 80% of core APIs and raised engineering efficiency 73%.
Research experience
Nov 2023 — Feb 2024
LLM4ITD: Insider Threat Detection with Fine-Tuned LLMs
Reformulated classification tasks as question-answering with structured prompts and parameter-efficient tuning of about 0.01% of parameters on CERT 4.2. AUC reached 0.9923, Recall 98.83%, training time was 30% lower, and compute was over 50% lower.
Aug 2023 — Oct 2023
Yellow Crane Tower Tourism Dialogue System
Extended and reparameterized RoPE and applied LoRA to Llama 2 7B. Built approximately 15,000 GPT-4-distilled tourism dialogues, with about 89% answer accuracy in human evaluation.
Jun 2023 — Oct 2023
Efficient Text Search Algorithm Evaluation
Collaboration with Prof. David Manlove. Evaluated seven algorithms on a 1M+ NLTK corpus and developed an Ukkonen-based suffix-tree approach with approximately 5.2× speedup. Applied it to human genomic sequences, improving search speed by 40% and reaching 100% accuracy in the reported evaluation.
Apr 2023 — Jul 2023
Lung Cancer Literature Classification with BioBERT
Expanded the dataset by approximately 6,000 samples through synonym replacement and back-translation, fine-tuned BioBERT with hierarchical freezing, and reached 93% PubMed accuracy with about 15% improvement on the manual evaluation set.
Jan 2023 — Jun 2023
EEG Feature Analysis for SCI Patients
Applied feature-selection methods to 5,000 samples: KNN improved 69.4% → 77.8%, and SVM reached 94.4%.
Nov 2022 — Jan 2023
ML Analysis of WSI Colorectal Cancer Datasets
Applied BERT-based augmentation to around 25% of the dataset and evaluated KMeans, Louvain, PCA, and UMAP.
Education
Sep 2022 — Dec 2023
University of Glasgow
MSc in Computer Science
GPA 3.67 / 4.0
Research collaboration with Prof. David Manlove, University of Glasgow professor and University of Oxford graduate.
Sep 2016 — Jun 2020
Hubei University
BEng in Software Engineering