5 papers
SKIP: a Self-knowledge-guided Step-wise Preference Learning Framework for Concise Reasoning
Qinhong Lin, Yuhao Zhang, Yinglun Feng +2
While Chain-of-Thought (CoT) reasoning has been proven to be effective, it often leads to overthinking, resulting in computational overhead, inference latency, and even degraded pe…
FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment
Qinhong Lin, Ruitao Feng, Yinglun Feng +7
We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement that mined factors be directly exec…
Provably Secure Retrieval-Augmented Generation
Pengcheng Zhou, Yinglun Feng, Zhongliang Yang
Although Retrieval-Augmented Generation (RAG) systems have been widely applied, the privacy and security risks they face, such as data leakage and data poisoning, have not been sys…
Why do AI agents communicate in human language?
Pengcheng Zhou, Yinglun Feng, Halimulati Julaiti +1
Large Language Models (LLMs) have become foundational to modern AI agent systems, enabling autonomous agents to reason and plan. In most existing systems, inter-agent communication…
Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
Pengcheng Zhou, Yinglun Feng, Zhongliang Yang
The widespread adoption of Retrieval-Augmented Generation (RAG) systems in real-world applications has heightened concerns about the confidentiality and integrity of their propriet…