Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
评测 coding agent 在非公开漏洞上的利用生成、修复与后续攻击
Published Oct 6
Evaluated models Opus 5 , GPT-5.6 Sol , GPT-6 Sol and others10 Abstract 攻防孰强随环境、系统和弱点改变。作者比较编程智能体在利用生成与漏洞修复上的自主表现，并检查修复之后还能不能被攻破。文中的 help 指自主完成任务，不是提升人类操作者。
提出 MobileCybench，用可执行探针评测 Agent 的漏洞发现能力
Published Sep 21
Evaluated models OpenCode/GPT-5.5 , OpenCode/GPT-5.6-Sol , OpenCode/GLM-5.2 and others5 提出 VLoc Bench，评测智能体在完整仓库中定位漏洞文件并抑制修复后误报
Published Sep 15
Evaluated models GPT-5.5 (xhigh) , GPT-5.5 (default) , Gemini 3 Pro and others15 Abstract 论文提出仓库级漏洞定位基准 VLoc Bench，指出当前模型定位表现较低且易在已修复代码上产生误报。
提出基准 PATCHBENCH，评测编程 Agent 的漏洞修补是否真正修复根因
Published Sep 4
Evaluated models Codex + GPT-5.6 Sol , OpenHands + GPT-5.6 Sol , Claude Code + Claude Opus 4.8 and others11 Abstract 论文揭示漏洞修复评测的记忆与表面防护问题，提出离栈变异基准与双重验证，测得智能体实际解决率仅约五成。
提出 SRE-Bench 评测智能体的真实规模二进制逆向能力
Published Aug 12
Evaluated models GPT-6-Astra , GPT-5.6-Sol , GPT-5.6-Cyber and others11 Abstract SRE-Bench 用从零编写的大规模保护二进制评测智能体 RE，公开设置下多数模型完全解开比例不高。作者构建并评测 SRE-Bench ，一个从零编写、用于测量智能体逆向工程而非利用开发的基准，并称它同时满足污染控制与真实软件规模。
提出 VulnGym 基准，评测编程智能体的仓库级漏洞检测并定位失败步骤
Published Aug 3
Evaluated models Qwen3.5-2B , Qwen3.5-4B , Qwen3.5-9B and others7 提出 OpenMLE，后训练元进化智能体并做机器学习工程长程搜索
Published Jul 31
Evaluated models Frontis-MA1-35B , Frontis-MA1-30B Abstract OpenMLE 训练 Frontis-MA1-35B，用四个共享算子把 MLE 后训练和长程搜索接成元进化闭环。作者提出全栈 OpenMLE ，在机器学习工程里研究从进化到元进化的一步，并把递归自我改进视为更远目标。智能体要在延迟、有噪声的执行反馈下反复修改程序。作者认为公开系统很少同时提供可扩展环境、基于执行的后训练，以及部署该模型的长程进化搜索。
用 CryptanalysisBench 评测大模型的端到端密码分析能力
Published Jul 21
Evaluated models Claude Opus 4.8 , Claude Sonnet 5 , Claude Mythos 5 and others10 Abstract 提出真实密码原语分析基准，证实前沿模型具备显著分析能力并能发现未公开设计缺陷。
构建真实网络靶场基准，评测 AI 的端到端自主攻击能力
Published Jun 12
Evaluated models GPT-5.5 , Claude-Opus-4.7 , GLM-5.1 and others7 Abstract 构建开放多靶场评测基础设施 AGENTCYBERRANGE，测定前沿 AI 网络攻击能力并揭示其端到端规划短板。
You have reached the end