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
GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base
用GPT构建超大规模知识库GPTKB，支持浏览查询与审计，为LLM知识库的可信度提供新解法。
arXiv:2608.06992v1 Announce Type: cross Abstract: We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized fro…
3
Auditable Release Control for Pedagogical Leakage in LLM Tutors
针对LLM家教泄露答案的痛点，提出可审计发布控制，在安全与教学效用间找到平衡线。
arXiv:2608.00515v1 Announce Type: cross Abstract: Large language model tutors can be correct and helpful yet disclose an answer or decisive reasoning …
4
PEARL: Auditable Repair for Scientific Reasoning Graph Extraction
科学推理图提取新方法PEARL，实现可审计的图修复，提升透明度和可靠性
arXiv:2607.17917v1 Announce Type: new Abstract: Scientific Reasoning Graph Extraction (SRGE) aims to recover explicit links among observations, eviden…
5
A Methodology for Auditable Trustworthiness Levels in AI Lifecycle Governance
提出可审计可信度水平的方法论，覆盖AI全生命周期治理，为负责任AI落地提供系统化框架。
arXiv:2607.16130v1 Announce Type: cross Abstract: AI governance increasingly requires judgments about whether an AI system remains adequately trustwor…
6
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…
7
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…
8
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…
9
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…
10
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…
11
A Systematic Approach to Multi-Agent AI from Advanced Regulatory Control Theory: Safe and Auditable LLM Operator Agents for Process Control
用控制理论驯服多智能体LLM，为过程控制打造安全可审计的AI操作员。
arXiv:2606.30877v1 Announce Type: cross Abstract: Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet p…
12
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…
13
Toolkit for Your AI Scientists – Rigorous, Auditable and Verifiable
复杂AI代理行为一键可视化，人类研究员轻松掌控并随时干预，严谨可审计。
Article URL: https://github.com/ARA-Labs/Agent-Native-Research-Artifact Comments URL: https://news.ycombinator.com/item?id=48703174 Points: 3 # Commen…
14
OctaMem: Auditable memory for AI agents, no vector DB to run
AI代理记忆管理新方案，免去向量数据库，审计透明，值得关注。
Article URL: https://octamem.com Comments URL: https://news.ycombinator.com/item?id=48628724 Points: 2 # Comments: 0
15
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…
16
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…
17
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…
18
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…
19
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…
20
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, …