Guard models are used to prevent LLM agents from performing forbidden actions, but this alone does not guarantee safety. The paper shows that many agent trajectories contain unfulfilled safety‑critical obligations—actions that should have been performed—highlighting a new source of risk. To address this, the authors introduce ObligationBench, a benchmark of 240 expert‑validated trajectories, and develop ObligationGuard, a model that improves obligation detection recall and exact‑match rates over existing models.
arXiv:2606. 02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.
arXiv:2606. 09890v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective.
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.
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.
StepGuard introduces a step-level guard model that audits and checks tool actions before execution, addressing security risks in LLM-based agents. It is trained using StepGen, an automatic engine that generates safe and unsafe trajectories, and employs Balance-GRPO to dynamically balance learning between safe and unsafe actions. Experiments show StepGuard achieves high accuracy comparable to GPT-5.4 and significantly reduces attack success rates while minimally impacting utility.
arXiv:2609.39107v1 Announce Type: new Abstract: Large Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and...
arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.
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.
VEPA is a framework that enables the verified evolution of formal guardrails for lifelong large language model agents. It represents guardrails as formal policies of symbolic rules over typed agent events, and during deployment uses LLM‑guided feedback to propose policy patches that fix new failures while preserving correct behavior. A deterministic verifier accepts only structurally valid, conflict‑free policies, and an evidence‑aware authority layer activates verified rules only when sufficient supporting evidence exists, ensuring that uncertain updates do not directly affect guardrail decisions.
arXiv:2606. 02965v2 Announce Type: replace Abstract: As large language models gain tool access and are deployed as autonomous agents capable of editing records, executing transactions, and modifying infrastructure, we still evaluate them based on the sole metric of task completion.
arXiv:2607. 02599v1 Announce Type: cross Abstract: Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges.
arXiv:2608. 09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.