风险评测 · 研究方法

Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations

NUWA 研究解读 · 独立复核待完成

首次发表: 2026-10-07来源核验: 2026-10-25

风险监测

原始来源 ↗引用本记录 ↓

NUWA Research Note

研究问题研究设计与假设来源发现 NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源

模型辅助整理 · 选读原始全文或官方文章中的相关章节；尚未完成逐章节审计。

研究速读

NUWA 解读：可导航来源有助检查行为结论，但不能证明标签正确。

研究问题

长智能体运行如何保留可观察性与可审计性？

研究设计与假设

Transect将可复用任务行为定义与判官设置分开，在源链接时间线上对齐事件、令牌、子智能体和标签。

来源发现

个案分析近1,300万令牌的AI研发评测。

结论区分可靠性诊断与效度，后者需独立专家标注等额外证据。

NUWA 解读

NUWA 解读：可导航来源有助检查行为结论，但不能证明标签正确。

局限与相反证据

模型扫描器可能夸大信心或隐藏不确定性，单个研究例不验证所有科学工作。

研究与决策意义

模型建议：导出分析时保留源轮次、判官配置及分歧诊断。

精确来源位置

Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations · AbstractSelected original resource https://arxiv.org/html/2610.08364; sha256:15cf35ee7c1d3115d5dac5322b3352f66d9b2564d843dfac2b42e43cf09c6480; archived source capture; exact capture time not independently established
Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations · §2.2 Design principlesSelected original resource https://arxiv.org/html/2610.08364; sha256:15cf35ee7c1d3115d5dac5322b3352f66d9b2564d843dfac2b42e43cf09c6480; archived source capture; exact capture time not independently established
Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations · §3 Case Study: Reading an AI R&D Evaluation with TransectSelected original resource https://arxiv.org/html/2610.08364; sha256:15cf35ee7c1d3115d5dac5322b3352f66d9b2564d843dfac2b42e43cf09c6480; archived source capture; exact capture time not independently established
Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations · §4 ConclusionSelected original resource https://arxiv.org/html/2610.08364; sha256:15cf35ee7c1d3115d5dac5322b3352f66d9b2564d843dfac2b42e43cf09c6480; archived source capture; exact capture time not independently established

来源核查、数据提取、编辑批准与实验复现分别记录。方法说明 →

机构与角色

发布机构英国 AI 安全研究所

引用与复用

引用研究发现时请引用原始出版物；引用 NUWA 的整理与解释时，单独引用本站记录及对应快照。

BibTeX ↓RIS ↓记录与来源元数据 · JSON ↓阅读覆盖 · JSON 提交更正

原始出版物 · BibTeX

@misc{transect,
  title = {Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations},
  url = {https://www.aisi.gov.uk/research/transect-retaining-observability-for-long-horizon-llm-agent-evaluations},
  year = {2026},
  date = {2026-10-07},
  version = {Source capture 2026-10-25},
  note = {Source capture 2026-10-25}
}

NUWA 记录 · BibTeX

@misc{transect-nuwa,
  title = {Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/transect/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--transect.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--transect.json.}
}

证据快照 2026-10-29.1 · 索引更新 · RSS

参考文献

[1] Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations. 2026-10-07 ; Official publication masthead and article byline; Abstract; §2.2 Design principles
[2] Read the full paper