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

arXiv:2610.08082v1 Announce Type: new Abstract: 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 fine-tune the agent on chain-of-thought deliberation or compile natural-language guardrails into runtime checks, but they do so without exposing a structural, auditable verdict. We propose POLAR, a guardrail framework for small tool-calling agents that assesses reversibility through a structured two-layer ontology. POLAR assigns each action a graded reversibility score by deriving a candidate inverse sequence; calls failing a threshold are pruned before execution. Evaluated on au^2-bench across six agent models, POLAR improves mean task reward by 0.11 to 0.18 points on airline for four of six agents, but only eight of eighteen model--domain cells improve overall; retail and stronger agents often regress. POLAR provides an auditable structural check and characterizes its task-utility trade-offs. Reward is not a direct measure of prevented harm.

Related

• Right-to-Act: A Pre-Execution Non-Compensatory Decision Protocol for AI Systems
• JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
• ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
• Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

Source: arXiv cs.AI | 2026-10-07