← Back to all news
arXiv AI By Jiapeng Sun, Yujin Zhou, Han Zhu, Pengcheng Wen, Jiayi Zhou, Sirui Han, Yike Guo

PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety

Read the original on arXiv AI →

PASTABench introduces a benchmark of 1,139 multi-turn trajectories to evaluate proactive safety monitoring in large language models. It formalizes three dimensions of intervention—whether, when, and what risk—to address gaps in step-level isolation and post-hoc trajectory assessment. The study finds that proactive intervention is largely unsolved, with the best model achieving only 40.74% optimal-timing interventions, and reveals that smaller models’ safety scores are often driven by lexical overfitting rather than true risk comprehension.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jul 30

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions

arXiv:2607. 26820v1 Announce Type: new Abstract: As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk assessment to understand how risks emerge and unfold over long-horizon trajectories.

By Shi Lin, Peng Qian, Dinghao Liu, Renjie Sun, Sifan Wu, Dezhang Kong, Chenpei Wang, Xun Wang
llmsagentssafety
More like this →
arXiv AI
Aug 21

ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis

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.

By Yu Li, Haoyu Luo, Yuejin Xie, Yuqian Fu, Zhonghao Yang, Shuai Shao, Qihan Ren, Wanying Qu, Yanwei Fu, Yujiu Yang, Jing Shao, Xia Hu, Dongrui Liu
llmsagentsbenchmarkssafetydata-engineering
More like this →
arXiv Machine Learning
5d ago

SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs

SafeTune is a source‑available library that consolidates four safety‑intervention paradigms—post‑hoc weight recovery, safety‑constrained fine‑tuning, gradient‑based unlearning, and inference‑time steering—into a single, configuration‑driven workflow. It offers shared interpretability, evaluation, and deployment tools, and its modular registry allows easy addition of new methods, benchmarks, judges, models, and fine‑tuning domains. The authors demonstrate SafeTune with controlled comparisons and case studies in finance and medical deployments, showing how it characterizes safety drift, evaluates interventions on refusal‑behavior and capability metrics, and supports calibrated or layered mitigation.

By Pratinav Seth, Saisab Sadhu, Anshul Kaushal, Vinay Kumar Sankarapu
llmsfine-tuningbenchmarkssafety
More like this →
arXiv AI
Aug 7

DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model

arXiv:2608. 05695v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states, user data, and downstream services.

By Wenhao Lin, Chenyu Yu, Xingwei Lin, Sicong Cao, Xiang Chen, Lei Xue, Le Yu, Letian Sha, Chunming Wu
llmsagentsbenchmarkssafety
More like this →