arXiv AI October 7, 2026 By Yunju Kang, Seonghyeon Cho, Irene Li, Yeo-Chan Yoon, Chanjun Park

POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents

POLAR is a guardrail framework designed for small tool‑calling language‑model agents that evaluates the reversibility of each action using a two‑layer ontology. By assigning graded reversibility scores and pruning calls that fall below a threshold, POLAR aims to prevent operational risks before they occur. In experiments on the τ²‑bench across six agent models, POLAR increased mean task reward by 0.11 to 0.18 points on airline tasks for four of six agents, though improvements were limited to eight of eighteen model‑domain cells, with some domains showing regression.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

2d ago

POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents

LLM tool-use agents operate in dynamic environments where many actions carry operational risk. However, most safety mechanisms react only after errors manifest. Existing pre-emptive approaches either...

llms agents fine-tuning safety

arXiv AI

Jun 6

From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

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

llms agents safety

arXiv AI

Aug 7

DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model

arXiv:2608. 05695v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states, user data, and downstream services.

By Wenhao Lin, Chenyu Yu, Xingwei Lin, Sicong Cao, Xiang Chen, Lei Xue, Le Yu, Letian Sha, Chunming Wu

llms agents benchmarks safety

arXiv AI

Jun 16

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

arXiv:2606. 15899v1 Announce Type: cross Abstract: Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted.

By Ismail Hossain, Sai Puppala, Md Jahangir Alam, Tanzim Ahad, Sajedul Talukder

llms agents benchmarks

arXiv AI

Aug 5

$S^3$: Improving Agent Safety through Multi-Stage Defense

arXiv:2608. 02683v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks.

By Zibo Xiao, Haoyu Wang, Jun Sun

llms agents benchmarks safety

arXiv AI

Sep 17

HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark

HINTBench is a new benchmark for evaluating agents’ intrinsic risk, comprising 596 trajectories (400 synthetic risky, 136 synthetic safe, 30 real risky, 30 real safe) with an average length of 24 steps. It supports three tasks—risk detection, risk-step localization, and intrinsic failure-type identification—using a unified five-constraint taxonomy. Experiments show a large performance gap: while large language models can detect risky trajectories, they score below 37 on strict-F1 for risk-step localization, and existing guard models transfer poorly to this setting.

By Jiacheng Wang, Jinchang Hou, Fabian Wang, Ping Jian, Chenfu Bao, Zhonghou Lv

llms agents benchmarks safety

One email a morning, machine-written

Related stories

POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents

From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

$S^3$: Improving Agent Safety through Multi-Stage Defense

HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark