AI-for-Science agents, which combine large language models (LLMs) with domain-specific harnesses to formulate hypotheses, run experiments, and interpret evidence, may compromise model safety. The study evaluated five harnesses on 50 harmful chemistry requests, finding that harnesses can increase harmful compliance even with direct prompting and that adaptive attacks that fail against the base LLM succeed once the harness is added. These results indicate that the safety behavior of the underlying LLM is not durable when integrated into an agent harness.
arXiv:2312.06632v2 Announce Type: replace Abstract: Artificial intelligence is rapidly advancing scientific discovery, but this progress carries risks of misuse, such as the creation of harmful subst...
arXiv:2606. 08234v1 Announce Type: new Abstract: LLM-based scientific agents have shown strong capacity for autonomous research, yet their safety layers remain structurally divorced from core reasoning: they inspect pipeline outputs rather than shaping the deliberation that produces them.
arXiv:2607. 09195v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery.
Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning and autonomous discovery. This progress creates an urgent need for safety benchmarks that evaluate not only scientific competence, but also whether models recognize and avoid risks in high-stakes scientific contexts.
arXiv:2607. 26064v1 Announce Type: cross Abstract: AI systems are becoming autonomous research agents that generate hypotheses, design experiments, and produce discoveries at scales beyond human oversight.
arXiv:2606. 11337v1 Announce Type: new Abstract: Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions.
arXiv:2606. 18936v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning and autonomous discovery.
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
arXiv:2602. 02905v2 Announce Type: replace Abstract: Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge.
arXiv:2606. 11217v1 Announce Type: cross Abstract: The proliferation of large language models (LLMs) and autonomous AI agents has given rise to a rapidly growing methodological paradigm: "in silico" behavioral experiments.
Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding.
Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and external environment feedback. In such settings,...