SIGMA is a self‑improving alignment framework that uses a model’s own reasoning to generate diverse alignment dilemma scenarios from a simple "Model Spec" and then fine‑tunes the model with self‑judged rewards. By performing spec‑guided task synthesis and rubric‑based reinforcement learning, SIGMA improves safety alignment in multi‑turn agentic settings, reducing harmfulness and misalignment scores while preserving general capability. The approach demonstrates that a model can autonomously strengthen its own safety reasoning without external supervision.
By Jingyu Zhang, Shruti Palaskar, Daniel Khashabi, Benjamin Van Durme, Leon A. Gatys, Joseph Yitan Cheng
arXiv:2607. 11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable.
By Xutao Mao, Xiang Zheng, Cong Wang
Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools.
The paper introduces the concept of Evolutionary Safety for recursive self-improving AI, focusing on how safety properties evolve as an AI system and its successors change. It identifies key risks such as intent drift, error accumulation, and safety-property erosion, and presents a taxonomy covering agent state, model state, evaluation, environment, and update mechanisms. The authors propose methods for discovering and evaluating evolutionary risks, and outline governance principles for modification, selection, authorization, provenance, and recovery, while highlighting open problems for maintaining safety in persistent, adaptive, and recursively self-improving systems.
By Chang Gong, Jingping Bi, Di Yao, Xinjian Liang, Chao Xiang, Ruijie Guo
Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.
arXiv:2606. 20408v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized.
By Hanwool Lee, Dasol Choi, Bokyeong Kim, Seung Geun Kim, Haon Park
arXiv:2606. 20408v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized.
By Hanwool Lee, Dasol Choi, Bokyeong Kim, Haon Park, Seung Geun Kim
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
By Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang
StepSafe introduces a training framework called ASPO that focuses on step‑level timely intervention in agentic systems. It aligns decisions with their respective prefixes, rewards actions that fit the current stage, and uses adaptive feedback self‑distillation to credit reasoning. The resulting StepSafe guardrail achieves state‑of‑the‑art performance on five agent‑safety benchmarks, improving the safety‑utility Pareto curve with a Youden’s J of 53.0 for a 4B model.
By Siyi Gu, Kunhan Gao, Chao Peter Yang, Sukanta Ganguly, Rex Ying, Arman Cohan
arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.
By Guoli Wang, Haonan Shi, Tu Ouyang, An Wang
arXiv:2506. 07121v2 Announce Type: replace Abstract: Ensuring the safety and robustness of large language models (LLMs) is a fundamental challenge and a critical prerequisite for the responsible deployment of artificial intelligence.
By Ren-Jian Wang, Ke Xue, Zeyu Qin, Ziniu Li, Sheng Tang, Hao-Tian Li, Shengcai Liu, Zhi Yu, Yuanpeng Tan, Chao Qian
The paper introduces SCOPE, a method that post‑trains computer‑use agents to balance task completion with safety by conditioning actions on environmental risk. It combines supervised fine‑tuning on three trajectory types—capability demonstrations, safe continuations, and explicit refusals—followed by reinforcement learning to improve performance. Experiments starting from Qwen3.5‑9B show that SCOPE‑RL achieves high task success and attack‑avoidance rates, outperforming other agents on OSWorld and OS‑BLIND benchmarks.
By Zeyu Kang, Zhenyun Yin, Yang Zhang, Shan He, Shanzhe Lei, Yanjiu Zhong, Xinquan Chen, Yuhong Wang