agent/papers/items/2026-2604-02022-atbench-a-diverse-and-realistic-agent-trajectory-benchmark-for-safety-evaluation.md

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

---

type: paper title: "ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis" authors: Yu Li, Haoyu Luo, Yuejin Xie, Yuqian Fu, Zhonghao Yang, Shuai Shao, Qihan Ren, Wanying Qu, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2604.02022 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-04-02 updated_at: 2026-05-13 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• planning
• rag
• tool-use methods:

benchmarks:

models:

datasets:

• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 20 collection_queries: agent-safety

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-safety
• inferred topics: agent-evaluation, agent-safety, planning, rag, tool-use
• arXiv categories: cs.AI
• collection score: 20

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2604.02022