Evolaris: A Roadmap to Self-Evolving Software Intelligence Management
Chengwei Liu, Wenbo Guo, Yuxin Zhang, Limin Wang, Sen Chen, Lei Bu, Yang Liu
TL;DR
The paper addresses the fragmentation and timeliness gaps in software threat intelligence by proposing Evolaris, a self-evolving software intelligence platform built on a collaborative, multi-agent architecture that automates the full lifecycle of threat information processing. It details two core components—Intelligence Discovery and Knowledge Evolution Platform—and describes how agents autonomously discover sources, interpret data, complete missing information, validate threats with root-cause analysis and PoC generation, and derive refined risk-detection rules. Early results show broad source integration (over 30 authoritative and 100 open sources), handling more than 260,000 vulnerabilities, and analyzing over 30,000 malicious code implementations, indicating strong scalability and practical relevance. The work emphasizes continuous, context-aware evolution of threat models and detection capabilities, offering a foundation for proactive software security analysis beyond traditional static approaches.
Abstract
In recent years, the landscape of software threats has become significantly more dynamic and distributed. Security vulnerabilities are no longer discovered and shared only through formal channels such as public vulnerability databases or vendor advisories. Increasingly, criti- cal threat information emerges informally through blogs, social media, developer forums, open source repositories, and even underground com- munities. To this end, capturing such intelligence in a timely manner is essential for maintaining situational awareness and enabling prompt security responses. However, this remains a complex challenge due to the fragmented nature of data sources and the technical difficulty of collecting, parsing, mapping, and validating information at scale. To ad- dress this, we propose Evolaris, a self-evolving software intelligence sys- tem built on a multi-agent framework. Evolaris is designed to support a full-stack workflow, where agents operate independently but coordinate through shared context to perform tasks such as information discovery, reasoning, gap completion, validation, and risk detection. This archi- tecture enables the platform to learn from new inputs, refine its internal knowledge, and adapt to emerging threat patterns over time, which could continuously improve the precision, timeliness, and scalability of software threat analysis, and offers a sustainable foundation for proactive secu- rity decision-making and strengthens the broader ecosystem of security threat understanding.