English(EN) LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents

新系统 LEDGER 助力 LLM 代理工作流审计

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-20 04:00

研究人员开发了 LEDGER 系统，用于审计大型语言模型 (LLM) 代理的输出。LEDGER 从代理会话构建分层追踪图，将执行事件组织成证据和工作流节点。这些图使用语义边将声明与支持性操作、工件和验证步骤连接起来，从而能够详细审查工件溯源、修复过程和以证据为中心的审计的声明支持路径。 AI

影响为验证 LLM 代理输出的正确性和可信度提供了一种结构化方法，这对于复杂、长周期的任务至关重要。

排序理由这是一篇描述用于审计 LLM 代理的新系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇描述用于审计 LLM 代理的新系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 75 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Daehong Kim, Haichao Miao, Shusen Liu · 2026-08-20 04:00

LEDGER：用于审计 LLM Agent 的声明到证据追踪图

arXiv:2608.18398v1 Announce Type: cross Abstract: Large language model (LLM) agents can now carry out long-horizon technical workflows involving complex tool use, code execution, file edits, and generated artifacts. As agents do more work faster, the productivity bottleneck shift…