Pai 的 AI 雷达

安全治理

今天：Beyond Unsafe Detection（Agent 原型），Narrative Paradoxes in（arXiv:2610）。

日期: 2026/10/15
今日条目: 103
当前类目: 2

往期2026/10/15

全部103编码代理6 Agent与工具10 个人助理7 模型与评测34 创作成片14 开发与开源11 产品接入21

领域机器人具身6 硬件边缘1 生信医疗3 法律合规2 金融2 安全治理2 行业观察5 创业者1

Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures

arXiv:2609.27773v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) move from conversational assistants to advanced agentic systems, guardrail failures can convert adversarial intents into harmful executions. However, most evaluation frameworks focus only on

arxiv.org打开原文

#02

Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment

arXiv:2610.16312v1 Announce Type: new Abstract: Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We identify a distinct challenge: ensuring the safety of

arxiv.org打开原文