arXiv:2607. 17575v1 Announce Type: new Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt before making a safety decision, and (ii) multi-component supervised fine-tuning (MC-SFT), a structured training loss for reasoning-based guardrails that decomposes LLM outputs into logical components and weights them according to their importance.
By Md Asiful Islam, Mihai Surdeanu
arXiv:2606. 05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categories, and/or explanatory rationales about potential policy violations.
By Yuhao Sun, Jiacheng Zhang, Shaanan Cohney, Zhexin Zhang, Feng Liu, Xingliang Yuan
arXiv:2607. 06326v1 Announce Type: new Abstract: Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation.
By He Liu, Changtao Miao, Xinjie Yang, Tianle Song, Yin Wu, Junchi Chen, Bintao He, Xinyuan Zhang, Bo Zhang, Shi Yan, Wei Lu, Wei Wang, Danyang Xu, Jiansheng Cai, Zhe Li
arXiv:2606. 25013v1 Announce Type: new Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts.
By Narutatsu Ri, Abhishek Panigrahi, Sanjeev Arora
arXiv:2606. 26686v1 Announce Type: new Abstract: In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict.
By Dongbin Na
arXiv:2606. 29887v1 Announce Type: new Abstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on predefined risk taxonomies.
By Jiacheng Zhang, Haoyu He, Sen Zhang, Shen Wang, Xiaolei Xu, Yuhao Sun, Meng Shen, Feng Liu
arXiv:2604. 15579v2 Announce Type: replace-cross Abstract: There is increasing interest in integrating AI agents that invoke tools into domain-specific commercial software, where unintended tool calls can cause serious security and safety incidents.
By Yining Hong, Yining She, Eunsuk Kang, Christopher S. Timperley, Christian K\"astner
arXiv:2507. 09751v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but exhibit problems with logical consistency in their output.
By Bradley P. Allen, Prateek Chhikara, Thomas Macaulay Ferguson, Filip Ilievski, Paul Groth
arXiv:2606. 23938v1 Announce Type: new Abstract: Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are attractive because they leverage pretrained VLM representations and expose intermediate decisions in natural language, yet current rationales often lack the step-by-step decision semantics needed to keep the rationale causally connected to the planned motion.
By Xiangbo Gao, Xiukun Huang, Boyu Lu, Junge Zhang, Mengjie Mao, Jiachen Li, Wei Xiong, Zhengzhong Tu
arXiv:2607. 21401v1 Announce Type: cross Abstract: A vision-language AI assistant returns its answer as a stream of generated tokens.
By Dongbin Na
arXiv:2510. 20692v3 Announce Type: replace-cross Abstract: Access control policies are reliability-critical configuration artifacts in cloud systems, yet administrators frequently struggle to verify that a policy permits exactly what they intend.
By Adarsh Vatsa, Bethel Hall, William Eiers
arXiv:2606. 01991v1 Announce Type: new Abstract: As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents unsafe capabilities and underscores the risk of power-seeking.
By Lichao Wang, Zhaoxing Ren, Tianzhuo Yang, Jiaming Ji, Chi Harold Liu, Yaodong Yang, Juntao Dai