Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
Proposes the FAITH safe filtering reinforcement learning framework, training high-dimensional systems to optimize task reward under constraints
Published Oct 9 Abstract FAITH separates safety filtering from reward optimization.FAITH is a model-free safe filtering reinforcement learning framework for high-dimensional systems: safety correction and task reward reside in separate modules.
提出 SIGMA，让模型依据 Model Spec 自造对齐数据并改进安全对齐
Published Oct 6
Evaluated models Qwen3.6-27B Abstract SIGMA 用 Model Spec 自造监督，单轮训练可迁到多项智能体安全指标。SIGMA 让 Qwen3.6-27B 只凭 Model Spec 和高层领域，自己生产对齐任务、评分细则和奖励。
提出 RAISED 自蒸馏，训练工具智能体抵御间接提示注入
Published Oct 5
Evaluated models Gemma-4-12B-it , Nemotron-3-Nano-30B-A3B , Qwen3.8-27B 提出 SRFT，让 Agent 从失败经验中学习拒绝提示注入
Published Oct 3
Evaluated models SR-Agent-Llama , SR-Agent-Qwen3-8B , SR-Agent-Qwen3-4B 提出 CorrGRPO，用 Pearson 相关归一化多奖励优势
Published Sep 29
Evaluated models Qwen2.5-Coder-0.5B-Instruct , Qwen2.5-Coder-1.5B-Instruct , Qwen2.5-Coder-3B-Instruct and others8 Abstract CorrGRPO 用 Pearson 相关归一化多奖励 GRPO 优势，并在三个域报告改进。CorrGRPO 是 GRPO 的多奖励变体：组内优势的分子仍是中心化总奖励，分母改为 Pearson 相关之和，避免大尺度奖励主导归一化。
提出协同演化防御 CoDeL，抵御智能体的间接提示注入
Published Sep 28
Evaluated models Qwen2.5-7B-Instruct , Llama-3.1-8B-Instruct 提出 SafeEvolve，用轨迹证据协同演化安全 harness 与策略
Published Sep 3
Evaluated models Qwen3.5-4B , Qwen3-4B-Instruct-2507 , Qwen3.5-1.7B and others4 Abstract SafeEvolve 用轨迹证据协同更新安全 harness 和策略，在两个 4B 模型的智能体安全基准上改变安全与效用。SafeEvolve 把已完成的 on-policy 轨迹变成安全 harness 的有界更新，并用两阶段 SFT-RL 把这些更新内化进工具使用策略。
提出 SCOPE，联合后训练计算机使用智能体的任务能力与安全决策
Published Aug 27
Evaluated models SCOPE-mid-checkpoint , SCOPE-Capability-Safety , SCOPE-RL You have reached the end