arXiv:2606. 00611v1 Announce Type: new Abstract: Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation.
arXiv:2605.27690v2 Announce Type: replace-cross Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate st...
arXiv:2608.15242v4 Announce Type: replace Abstract: In long agent executions, an early error can persist through later actions and checks, while evidence needed to trace its origin is dispersed acros...
arXiv:2606. 07054v1 Announce Type: cross Abstract: Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring.
arXiv:2604. 02022v4 Announce Type: replace Abstract: Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses.
arXiv:2608. 06346v1 Announce Type: new Abstract: LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging.
arXiv:2608. 15242v1 Announce Type: new Abstract: When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the trajectory.
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:2607. 19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compose into harm.
arXiv:2607. 26820v1 Announce Type: new Abstract: As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk assessment to understand how risks emerge and unfold over long-horizon trajectories.
arXiv:2606. 31650v2 Announce Type: replace-cross Abstract: Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows.
arXiv:2608. 06909v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate through long-horizon trajectories involving user instructions, tool use, external observations, and memory.
arXiv:2606. 16313v1 Announce Type: cross Abstract: Long-tail scenarios remain a major bottleneck for autonomous driving evaluation, even as datasets grow by orders of magnitude.