arXiv:2606. 15899v1 Announce Type: cross Abstract: Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted.
arXiv:2606. 20502v1 Announce Type: cross Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved.
AMLworld-Compact introduces an importance‑weighted downsampling protocol for evaluating large language models on AMLworld’s test splits, retaining all illicit transactions while sampling benign ones from supervised‑score strata. The HT‑Coreset method reduces evaluation targets by 271× on HI‑Small and 611× on LI‑Small, providing unbiased confusion‑count estimates with exact recall and ratio estimates for precision and F1. Experiments with boosted‑tree strata and Graph Feature Preprocessor features show lower F1 RMSE compared to uniform sampling, and audit tools reveal that lexical checks do not reliably indicate correctness of model outputs.
arXiv:2608. 01388v1 Announce Type: cross Abstract: Runtime safety monitors based on Linear Temporal Logic (LTL) and finite automata (FSA) are increasingly deployed to intercept unsafe tool-call sequences in LLM agents.
End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present layer-isolated evaluation: a deployed ordering agent is decomposed into a fixed taxonomy of layers (ontology, intent, routing, decomposition, escalation, safety, memory, and cross-cutting envelope/defense), each exercised by its own assertion slice in a deterministic, no-LLM "pure" mode.
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:2606. 11686v1 Announce Type: cross Abstract: End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where.
arXiv:2608. 16391v1 Announce Type: cross Abstract: As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the ecosystem.
arXiv:2606. 00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set.
The paper introduces Conditional Accuracy Profiling (CAP), a diagnostic framework that breaks down LLM‑judge accuracy into eight deployment conditions covering content sensitivity, robustness, and rationale quality. CAP is benchmark‑agnostic and can be applied directly when annotations are available, via task‑subset proxies, or through controlled augmentation. Applied to seven judges across six benchmarks, CAP reveals that aggregate accuracy masks important differences—for example, judges highly sensitive to omitted qualifications rank poorly on a Hard‑Constructed subset, and Position Robustness is generally stable but can degrade sharply under adversarial stress.
The paper introduces D$^2$ACCI, a dual-loop diagnostic protocol designed to improve evidence-preserving memory in large language model agents. It provides stage-level diagnostic traces, protected-slice monitoring, and a graded observability metric (DCR) to localize failures within the memory pipeline. Applied to MemStack and evaluated on three benchmarks, the protocol achieves high accuracy and demonstrates statistically significant gains from specific memory interventions.
arXiv:2608.27580v2 Announce Type: replace Abstract: Safety guardrails serve as the last line of defense against harmful inputs and outputs of large language models (LLMs), yet they are trained and ev...