1
Auditable Agents
让AI智能体行为可追溯、可问责，破解黑箱难题的前沿研究
arXiv:2604.05485v2 Announce Type: replace Abstract: LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an…
2
Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction
提出显式可审计的图推理方法，通过目标感知的因果链构建实现推理路径透明化
arXiv:2607.15281v1 Announce Type: new Abstract: Causal and intervention-based question answering is fundamental to advancing large language models (LL…
3
Why LLM Decisions Should Be Deterministic
LLM决策的确定性边界关键不是一致性，而是可审计性——每个决策都有可复现的实现。
TL;DR: I originally treated deterministic boundaries around LLMs as a consistency mechanism. I now think their real value is auditability. If the syst…
4
Towards Autonomous and Auditable Medical Imaging Model Development
医学影像模型开发的未来方向：如何在自主生成的同时保证全流程可审计？这篇论文提出了新框架。
arXiv:2607.10522v1 Announce Type: cross Abstract: Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by co…
5
Auditable Workspaces for AI Coding Agents
聚焦AI编程代理的可审计性，探讨如何构建透明、可追溯的编码工作空间，提升代码质量与信任。
Article URL: https://medium.com/@Koukyosyumei/auditable-workspaces-for-ai-coding-agents-de00eff5f9b9 Comments URL: https://news.ycombinator.com/item?i…
6
Medical Heuristic Learning: An LLM-Driven Framework for Interpretable and Auditable Clinical Decision Rules
LLM驱动医学启发学习框架，生成可解释、可审计的临床决策规则，让AI医疗更可信。
arXiv:2606.16337v1 Announce Type: new Abstract: Predictive modeling for clinical tabular data is central to clinical decision support and therefore re…
7
AeroSpectra Sentinel: An Auditable LLM Prompt-Chaining Decision-Support Workflow for Acute Asthma Risk Assessment from Respiratory Sounds and Clinical Signals
基于呼吸音和临床信号，用可审计的LLM提示链工作流实现急性哮喘风险评估，医疗AI新突破。
arXiv:2606.08247v1 Announce Type: cross Abstract: Acute asthma risk assessment requires rapid interpretation of respiratory sounds, oxygenation, airfl…
8
Provably Auditable and Safe LLM Agents from Human-Authored Ontologies
基于人类编写本体论，实现LLM代理的可证明安全与可审计性，为智能体可靠性提供新路径。
arXiv:2606.04903v1 Announce Type: cross Abstract: We introduce the LLM agent architecture Agentic Redux, intended for use with nontrivial problem doma…