agent/papers/items/2026-2605-08876-otora-a-unified-red-teaming-framework-for-reasoning-level-denial-of-service-in-l.md

Paper: OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents

---

type: paper title: "OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents" authors: Xinyu Li, Ronghui Mu, Lin Li, Tianjin Huang, Gaojie Jin year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.08876 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-09 updated_at: 2026-06-07 status: queued relevance: high topics:

• computer-use
• reasoning
• tool-use methods:

benchmarks:

models:

datasets:

• cs.LG related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 13 collection_queries: autonomous-agent-llm

One-line Takeaway

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

Why Collected

• matched queries: autonomous-agent-llm
• inferred topics: computer-use, reasoning, tool-use
• arXiv categories: cs.LG
• collection score: 13

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/2605.08876