1
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…
2
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…
3
Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
为LLM智能体设计可审计的假设演化协议，让AI科学家过程透明可信
arXiv:2607.09195v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scient…
4
FirstResearch: Auditable Question Formation for LLM Scientific Discovery Agents
提出可审计的问题形成方法，让LLM科学发现代理更可靠、更透明，研究新思路值得一看
arXiv:2607.05682v1 Announce Type: new Abstract: LLM systems for scientific discovery increasingly assist with ideation, literature synthesis, experime…
5
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…
6
Deterministic Integrity Gates for LLM-Assisted Clinical Manuscript Preparation: An Auditable Biomedical Informatics Architecture
一种可审计的生物医学信息学架构，用确定性完整性门控确保LLM辅助临床手稿的准确与可信。
arXiv:2606.09500v1 Announce Type: new Abstract: Objective. Large language models (LLMs) increasingly draft clinical research manuscripts, but their fl…
7
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…
8
Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables
可审计的跨维基表格源前沿发现方法，保障LLM生成表格的溯源可靠性。
arXiv:2605.20478v1 Announce Type: new Abstract: LLM-curated tables can appear source-grounded while containing unsupported rows: the curator may recal…
9
Fully Open Meditron: An Auditable Pipeline for Clinical LLMs
完全开源且可审计的临床大模型流水线，解决AI医疗黑箱问题，数据来源与训练过程全透明。
arXiv:2605.16215v1 Announce Type: new Abstract: Clinical decision support systems (CDSS) require scrutable, auditable pipelines that enable rigorous, …