可追踪推理链让大模型检测虚假订单欺诈更可信，论文提出创新方法。
arXiv:2607.23075v1 Announce Type: cross Abstract: Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) s…
探索AI Agent技能可追溯性如何重塑UX设计，为设计流程注入透明与可控。
Article URL: https://rapidkt.com/pages/blog/ai_agent_skill_traceability_in_ux_design Comments URL: https://news.ycombinator.com/item?id=48846376 Point…
企业级AI模拟新框架OrgForge，用严格边界切断幻觉根源，让组织模拟可追溯可信赖。
Article URL: https://www.machinebrief.com/news/orgforge-the-next-step-in-enterprise-ai-simulation-u364 Comments URL: https://news.ycombinator.com/item…
一个把人与AI对话转化为可追溯、可审计指标的实验原型，为AI监管提供可视化抓手。
arXiv:2606.29437v1 Announce Type: cross Abstract: The growing use of Large Language Models (LLMs) in education, software engineering, academic writing…
为AI系统提供执行来源追踪的开源工具，提升模型行为可追溯性
Article URL: https://github.com/Therealdk8890/DProvenanceKitPython Comments URL: https://news.ycombinator.com/item?id=48743043 Points: 1 # Comments: 0
让AI智能体干活时自动截图留证，用真实屏幕记录验证每一步操作，防忽悠神器。
Article URL: https://github.com/varmabudharaju/shotlist Comments URL: https://news.ycombinator.com/item?id=48682204 Points: 4 # Comments: 1
一份面向医疗AI的全球日志体系，让关键的AI事件可追溯、可审计，理解系统如何记录与复现。
arXiv:2510.04033v2 Announce Type: replace Abstract: Modern computer systems rely on syslog, a universal protocol that records critical events across h…
在自有Postgres上为AI代理构建源可追溯记忆的开源方案，兼顾隐私与可控性
Article URL: https://github.com/thegoodguysla/myco-brain Comments URL: https://news.ycombinator.com/item?id=48589516 Points: 1 # Comments: 0
提出简洁的智能体行为水印框架，为AI Agent的可追溯性与安全性提供新思路。
arXiv:2504.05871v3 Announce Type: replace Abstract: The increasing deployment of intelligent agents in digital ecosystems, such as social media platfo…
用LLM管道和交互仪表盘自动化提取欧盟监管咨询中的结构化主题，实现可追溯分析。
arXiv:2605.30995v1 Announce Type: cross Abstract: Public consultations generate large volumes of data in the form of stakeholder submissions that are …
ISSTA '26收录的实证研究，首次从可追溯性视角系统评估自动化程序修复智能体的行为与效果。
arXiv:2506.08311v2 Announce Type: replace-cross Abstract: Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously …