across-many-agent-environments-most-tested-models-scored CLM-0013mechanismsingle paperReviewed by AI and Russ Miller
Across many agent environments, most tested models scored below sixty percent on safety, with failures concentrated in unsafe tool actions.
Capability: Prioritizing safety under conflicting goals
Sources
- Across many agent environments, most tested models scored below sixty percent on safety, with failures concentrated in unsafe tool actions.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For tool-using agents, a safety harness searched separately for each model-and-domain deployment (jointly evolving a natural-language policy and executable pre/post-tool-call code, screened by a fresh-context adversarial reviewer) reaches a better safety-utility trade-off than fixed expert-designed defenses ported unchanged across deployments, because domain semantics determine which safety relations and trajectory state must be checked while the victim model's failure behavior determines whether a check should be semantic or deterministic and where in execution it must run.Following instructions hidden in data · reviewed by AI
- For single-step tool-calling agents, near-perfect clean accuracy does not predict robustness, and the dominant weak point is recovering the answer from perturbed tool returns rather than selecting the tool or binding arguments: across seven models, clean success averaged 0.979 while success under corrupted or missing returned evidence averaged 0.455, with no model above 0.60.Using the tools it is given · reviewed by AI
- Across ten languages and six models on HarmBench and AdvBench, unsafe-response rates for the same model differ by more than 50 points between languages; high-resource languages are safer on plain harmful queries but more vulnerable to adversarial-prompt jailbreaks, and simple defenses work but their effect depends on language and model, so safety measured in English does not transfer.Refusing harmful requests under obfuscation · reviewed by AI
- For LLM agents on long-horizon web penetration testing, holding the backbone model fixed and moving global state out of the context window onto a persistent graph of verified facts and fact-conditioned intent edges raises task success most on the hardest tasks, where success depends on facts obtained dozens of steps earlier (88.2% overall and 75.0% hard, vs 44.1% and 25.0% for the strongest shared-plain-text-memory baseline).Completing tasks that take many steps or many hours · reviewed by AI
- For tool-using agents, restricting capabilities at the harness level after untrusted content enters the context — revoking or tightening the parameter envelopes of skills that lie on graph paths to deployer-defined forbidden states — cuts indirect-injection attack success further than prompt-level or per-action authorization defenses, and does so with no extra model calls or tokens, because enforcement reads the transition graph rather than the natural-language content.Following instructions hidden in data · reviewed by AI