arXiv:2606. 04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5 models (12B--70B) in 4,200 interactions with dual-judge validation.
arXiv:2607. 19449v1 Announce Type: cross Abstract: Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited.
arXiv:2608.20554v1 Announce Type: cross Abstract: The critical failure modes in deployed large language models (LLMs) are cross-dimensional: a model can score 99.3 in safety alignment while refusing...
arXiv:2609.39050v1 Announce Type: cross Abstract: As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has e...
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
arXiv:2607. 02714v1 Announce Type: cross Abstract: There is no doubt that safety alignment is an essential step in LLM training.
The paper introduces FUSE, a modular framework that evaluates large language models (LLMs) for dangerous capabilities across three orthogonal pipelines: Knowledge (K), Defense (D), and Harm (H). Using a chemical‑biological module, the authors assess 12 commercial LLMs, revealing divergent profiles among models and families, and showing that newer models increase knowledge while only partially improving defense. The framework’s reliability is supported by high cross‑judge consistency and low inter‑pipeline correlations.
The paper investigates whether large language models decide to gather safety-relevant evidence before acting. Using the SAFE benchmark, the authors evaluate models such as GPT‑5.5, o3, Claude Opus, and Claude Sonnet, finding distinct evidence‑acquisition strategies that vary with retrieval cost, severity, and presentation. Across models, expected‑value reasoning dominates Stage 1 rationales, and evidence framing can alter decisions near the inspection threshold while probability is often cited despite limited influence.
The paper introduces ‘Fool’s Gold’, a defensive deception technique for open‑weight language models that hardens them against safety‑removal attacks. By training decoy responses within a differentiable simulation of the attack, the method poisons the payoff of stripped refusal mechanisms, producing confident but falsified answers to hazardous requests while preserving benign behavior. Experiments on seven models (9B‑122B) show that 51‑90% of attacked‑state responses become decoys, with the defense accounting for 27‑84% of this effect, and that the defended 122B model remains within benign‑behavior budgets.
arXiv:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.
arXiv:2607. 07695v1 Announce Type: new Abstract: We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule.
arXiv:2606. 00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set.
arXiv:2606. 15242v1 Announce Type: cross Abstract: Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, and tool misuse.