Abstract
Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform. However, identifying forbidden actions alone is insufficient to ensure agent safety. In this paper, we argue that agent safety also depends on identifying required yet unperformed safety-critical actions, which we call obligations. Our preliminary study on a popular benchmark for evaluating safety shows that 56.92% of GLM-5.3 trajectories contain unfulfilled obligations, compared with only 30.00% containing forbidden actions. This finding reveals unfulfilled obligations as a major and previously overlooked source of safety risk. However, to our knowledge, no existing benchmark evaluates whether guard models can identify these obligations. To close this gap, we introduce ObligationBench, the first benchmark for evaluating the capability of obligation identification, comprising 240 expert-validated trajectories covering issue resolution, feature development, and terminal operations. Our evaluation of 14 representative models reveals substantial limitations: the highest recall and exact-match rate are only 48.97% and 10.00%, respectively. To address these limitations, we develop ObligationGuard using 40,000 synthetic training examples. ObligationGuard achieves 57.52% recall and an exact-match rate of 21.67%, surpassing all evaluated models on both metrics. We call on the community to incorporate obligation identification into the design and evaluation of future guard models to improve agent safety.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Feng, Y., Zhang, Y., Liu, Y., & Li, J. (2026). Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models. https://omanscience.com/en/articles/safe-actions-alone-do-not-ensure-safe-agents-identifying-unfulfilled-obligations-with-guard-models
MLA 9
Feng, Youwei, et al. "Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models." https://omanscience.com/en/articles/safe-actions-alone-do-not-ensure-safe-agents-identifying-unfulfilled-obligations-with-guard-models.
Chicago (author–date)
Feng, Youwei, Yitong Zhang, Yuetong Liu, and Jia Li. 2026. "Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models." https://omanscience.com/en/articles/safe-actions-alone-do-not-ensure-safe-agents-identifying-unfulfilled-obligations-with-guard-models.
Harvard
Feng, Y., Zhang, Y., Liu, Y. and Li, J. (2026) 'Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models', Available at: https://omanscience.com/en/articles/safe-actions-alone-do-not-ensure-safe-agents-identifying-unfulfilled-obligations-with-guard-models.
Vancouver
Feng Y, Zhang Y, Liu Y, Li J. Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models. https://omanscience.com/en/articles/safe-actions-alone-do-not-ensure-safe-agents-identifying-unfulfilled-obligations-with-guard-models
IEEE
Y. Feng, Y. Zhang, Y. Liu, and J. Li, "Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models," https://omanscience.com/en/articles/safe-actions-alone-do-not-ensure-safe-agents-identifying-unfulfilled-obligations-with-guard-models.