5 papers
Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs
Jiacheng Xu, Wentao Zhang, Zhiyi Lyu +4
Reinforcement learning (RL) has substantially advanced code generation with large language models (LLMs) through executable feedback. The feedback for coding problems mainly comes…
Autogenesis: A Self-Evolving Agent Protocol
Wentao Zhang, Zhe Zhao, Haibin Wen +4
LLM-based agent systems can adapt by revising prompts, constructing tools, and changing other runtime resources. Managing these heterogeneous updates requires a shared lifecycle fo…
Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance
Yilei Zhao, Wentao Zhang, Lei Xiao +3
Environmental, social, and governance (ESG) criteria are essential for evaluating corporate sustainability and ethical performance. However, professional ESG analysis is hindered b…
AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol
Wentao Zhang, Liang Zeng, Yuzhen Xiao +7
Recent advances in LLM-based agent systems have shown promise on complex, long-horizon tasks, but existing agent protocols (e.g., A2A and MCP) do not adequately support lifecycle-a…
STORM: A Spatio-Temporal Factor Model Based on Dual Vector Quantized Variational Autoencoders for Financial Trading
Yilei Zhao, Wentao Zhang, Tingran Yang +3
In financial trading, factor models are widely used to price assets and capture excess returns from mispricing. Recently, we have witnessed the rise of variational autoencoder-base…