11 papers
SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning
Zhaohan Meng, Zaiqiao Meng, Siwei Liu +3
Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and phenotypes. Existing agents typ…
A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?
Zhaohan Meng, Zhen Bai, Ke Yuan +4
Protein-ligand modeling underpins computational drug discovery and molecular design. Existing protein-ligand benchmarks typically evaluate whether a protein and ligand interact and…
SEW: Self-Evolving Agentic Workflows for Automated Code Generation
Siwei Liu, Jinyuan Fang, Han Zhou +2
Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on cr…
EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning
Andreas Sauter, Yuyue Zhao, Jacopo Urbani +5
Scientific idea generation is a cornerstone of autonomous knowledge discovery, yet the iterative evolution required to transform initial concepts into high-quality research proposa…
GraphMed-LT: Patient-Specific Graph Memory with Latent Clinical Thought Refinement for Multi-Turn Medical Conversations
Zhaohan Meng, Zaiqiao Meng, Siwei Liu +3
Multi-turn medical question answering (QA) aims to model realistic clinical diagnosis, where a doctor gathers patient information across multiple turns of conversation. Existing mu…
EvoAgentX: An Automated Framework for Evolving Agentic Workflows
Yingxu Wang, Siwei Liu, Jinyuan Fang +1
Multi-agent systems (MAS) have emerged as a powerful paradigm for orchestrating large language models (LLMs) and specialized tools to collaboratively address complex tasks. However…