홈 › Papers

CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability

2026-02-03 · Xianzhen Luo, Jingyuan Zhang, Shiqi Zhou, Jinyang Huang, Chuan Xiao, Qingfu Zhu, Zhiyuan Ma, Xing Yue, Yang Yue, Wencong Zeng, Wanxiang Che arxiv

Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fully executable agentic tasks. Cross-validation against human expert reproductions shows that CVE-Factory achieves 95\% solution correctness and 96\% environment fidelity, confirming its expert-level quality. It is also evaluated on the latest realistic vulnerabilities and achieves a 66.2\% verified success. This automation enables two downstream contributions. First, we construct LiveCVEBench, a continuously updated benchmark of 190 tasks spanning 14 languages and 153 repositories that captures emerging threats including AI-tooling vulnerabilities. Second, we synthesize over 1,000 executable training environments, the first large-scale scaling of agentic tasks in code security. Fine-tuned Qwen3-32B improves from 5.3\% to 35.8\% on LiveCVEBench, surpassing Claude 4.5 Sonnet, with gains generalizing to Terminal Bench (12.5\% to 31.3\%). We open-source CVE-Factory, LiveCVEBench, Abacus-cve (fine-tuned model), training dataset, and leaderboard. All resources are available at https://github.com/livecvebench/CVE-Factory .

📄 PDF Abstract BibTeX arXiv:2602.03012

Code (0)

등록된 구현이 없습니다.

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

2026-06-29 · Lei Bai, Zongsheng Cao, Yang Chen, Zhiyao Cui 외 arxiv

We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-hori…

CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild

2026-08-24 · Jian Yang, Haau-Sing Li, Shawn Guo, Zixi Zhao 외 arxiv

As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention, with closed-source LLMs (e.g., Mythos) delivering advanced cybersecuri…

Question Answering

Position: Agentic AI System Is a Foreseeable Pathway to AGI

2026-05-13 · Junwei Liao, Shuai Li, Muning Wen, Jun Wang 외 arxiv

Is monolithic scaling the only path to AGI? This paper challenges the dogma that purely scaling a single model is sufficient to achieve Artificial General Intelligence. Instead, we identify Agentic AI as a necessary para…

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

2026-05-18 · Minrui Xu, Zilin Wang, Mengyi DENG, Zhiwei Li 외 arxiv

Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data…

Reinforcement Learning

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments

2025-09-26 · Hanlin Zhu, Tianyu Guo, Song Mei, Stuart Russell 외 arxiv

As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard to disentangle agentic reasoning when eva…