Research Projects

Selected research systems, benchmarks, datasets, and open-source implementations.

Agentic Systems

Strategic reasoning, collaboration, personalization, and secure code agents.

Top ⇈
ICLR 2026 Competition Multi-agent

TreeDebater

Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters

TreeDebater uses rehearsal and debate-flow trees to anticipate attacks, track active arguments, and allocate limited speaking time for more persuasive LLM debates.

Danqing Wang*, Zhuorui Ye*, Xinran Zhao*, Fei Fang, Lei Li

ICML 2026 Safety Code Agents Benchmark

SusVibes

Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks

SusVibes benchmarks 187 real-world feature requests and reveals a sharp gap between functional correctness and security in code produced by leading coding agents.

Songwen Zhao, Danqing Wang, Kexun Zhang, Jiaxuan Luo, Zhuo Li, Lei Li

ICLR 2025 Reasoning Multi-agent

TypedThinker

TypedThinker: Typed Thinking Improves Large Language Model Reasoning

TypedThinker predicts when to use deductive, inductive, abductive, or analogical reasoning and supplies targeted demonstrations to diversify LLM problem solving.

Danqing Wang, Jianxin Ma, Fei Fang, Lei Li

EMNLP 2024 Evaluation Personalization

PerSE

Learning Personalized Alignment for Evaluating Open-ended Text Generation

PerSE infers a reviewer's preferences from an in-context profile to deliver interpretable, fine-grained evaluations of how well open-ended generations align with that individual.

Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian

EMNLP 2023 Collaboration Multi-agent

SALAM

Learning from Mistakes via Cooperative Study Assistant for Large Language Models

SALAM pairs an LLM with a cooperative study assistant that records prior mistakes and retrieves tailored guidance to help the model avoid recurring reasoning errors.

Danqing Wang, Lei Li

AI for Science

Machine learning for molecular explanation, antibodies, and peptide discovery.

Top ⇈
KDD 2024 AI for Science Explainability

RLHEX

Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning

RLHEX combines a variational graph generator with reinforcement learning to produce global molecular counterfactual explanations aligned with human-defined principles.

Danqing Wang*, Antonis Antoniades*, Kha-Dinh Luong, Edwin Zhang, Mert Kosan, Jiachen Li, William Yang Wang, Ambuj Singh, Lei Li

ICLR 2023 AI for Science Antibodies Benchmark

EATLM & ATUE

On Pre-training Language Model for Antibody

EATLM and the ATUE benchmark examine how general and antibody-specific protein language models transfer across antibody tasks and where biologically informed pre-training helps.

Danqing Wang, Fei Ye, Hao Zhou

KDD 2023 AI for Science Peptides

LSSAMP

Accelerating Antimicrobial Peptide Discovery with Latent Structure

LSSAMP jointly models peptide sequences and secondary structures in a quantized latent space to generate antimicrobial candidates, two of which showed strong activity in wet-lab tests.

Danqing Wang, Zeyu Wen, Fei Ye, Lei Li, Hao Zhou

Text Summarization

Faithful, multilingual, graph-based, and cross-domain summarization.

Top ⇈
ACL Findings 2021 Summarization Multilingual Benchmark

CALMS

Contrastive Aligned Joint Learning for Multilingual Summarization

CALMS uses contrastive sentence ranking and sentence-aligned substitution to improve multilingual summarization in both high- and low-resource languages.

Danqing Wang, Jiaze Chen, Hao Zhou, Xipeng Qiu, Lei Li

NLPCC 2021 Summarization Dataset Benchmark

CNewSum

CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level

CNewSum provides 304,307 Chinese news documents with human-written summaries and test-set adequacy and deducibility annotations for diagnosing summarization systems.

Danqing Wang, Jiaze Chen, Xianze Wu, Hao Zhou, Lei Li

ACL 2020 Summarization Graph Neural Networks

HeterSumGraph

Heterogeneous Graph Neural Networks for Extractive Document Summarization

HeterSumGraph connects sentence nodes through finer-grained semantic units in a heterogeneous graph to enrich cross-sentence modeling for extractive summarization.

Danqing Wang*, Pengfei Liu*, Yining Zheng, Xipeng Qiu, Xuanjing Huang

arXiv 2019 Summarization Domain Shift

MULTI-SUM

Exploring Domain Shift in Extractive Text Summarization

MULTI-SUM defines summarization domains by data source, measures cross-domain generalization gaps, and provides a testbed for comparing four adaptation strategies.

Danqing Wang*, Pengfei Liu*, Ming Zhong, Jie Fu, Xipeng Qiu, Xuanjing Huang