arXiv:2606. 09878v1 Announce Type: new Abstract: Standard benchmarks report aggregate accuracy, but practitioners need to know which specific capabilities a model lacks.
arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.
arXiv:2608. 08700v1 Announce Type: new Abstract: Reliable evaluation of tool routing is critical as Large Language Models increasingly operate as autonomous agents.
The paper introduces the SAST-IR framework to evaluate large language models’ robustness against persuasion attacks in a memory‑less setting, revealing a flaw called "Refusal Inertia" that masks true vulnerability. Using the CP‑Agent and a custom CounterFact‑Strict dataset, the authors demonstrate that simple, diverse attack strategies achieve a 96% success rate, while complex attacks often trigger defensive compliance. The study highlights severe brittleness in current state‑of‑the‑art models when deprived of conversation history.
arXiv:2607. 28802v1 Announce Type: new Abstract: Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system.
arXiv:2508. 00923v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to answer health-related questions and support healthcare workflows, yet evidence for their safety still relies heavily on static benchmarks that can rapidly become obsolete or be optimized against.
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
The paper introduces an action‑class diagnostic framework for multi‑turn tool‑calling in large language model agents, breaking failures into action‑class miscalibration and action‑execution failure across a four‑class action space (TOOL_CALL, ASK, REFUSE, CONFIRM). It defines a self‑revealing upper bound (Acc GAR) to expose state‑grader masking of miscalibration and shows that miscalibration is a significant, previously hidden failure mode, especially for heavily tool‑trained families. The study demonstrates that calibration can be reshaped by context‑only perturbations, but the effects vary widely across models and perturbation mechanisms, underscoring the need for diagnostics beyond aggregate accuracy.
arXiv:2607. 07474v1 Announce Type: cross Abstract: Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not.
The paper introduces Continual Search, an iterative framework that guides large language models to persistently search for diagnostic evidence in long AI agent execution logs, addressing the limitations of one-shot judgments. Evaluated on four existing RCA benchmarks and a new large-scale dataset called MegaRCA-Mix, Continual Search consistently boosts attribution performance, achieving a 40% F1 improvement for GPT‑5.5 on MegaRCA‑Mix. The results show that effective search can outweigh raw model scale, enabling lower-tier models to outperform higher-tier ones in root‑cause attribution tasks.
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. 16387v1 Announce Type: cross Abstract: An agent system's execution traces record how it fails, and procedures that improve such a system without changing model weights (trajectory selection, prompt and workflow optimization, runtime monitoring) read these traces for feedback.
arXiv:2607. 01153v3 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agentic task.