AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks

• URL: http://arxiv.org/abs/2602.16901v1
• Date: Wed, 18 Feb 2026 21:30:20 GMT
• Title: AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
• Abstract summary: We present AgentLAB, the first benchmark dedicated to evaluating agent susceptibility to adaptive, long-horizon attacks.<n>AgentLAB supports five novel attack types including intent hijacking, tool chaining, task injection, objective drifting, and memory poisoning.<n>We find that representative LLM agents remain highly susceptible to long-horizon attacks.
• Score: 10.74152341304056
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interactions to achieve objectives infeasible in single-turn settings. To measure agent vulnerabilities to such risks, we present AgentLAB, the first benchmark dedicated to evaluating LLM agent susceptibility to adaptive, long-horizon attacks. Currently, AgentLAB supports five novel attack types including intent hijacking, tool chaining, task injection, objective drifting, and memory poisoning, spanning 28 realistic agentic environments, and 644 security test cases. Leveraging AgentLAB, we evaluate representative LLM agents and find that they remain highly susceptible to long-horizon attacks; moreover, defenses designed for single-turn interactions fail to reliably mitigate long-horizon threats. We anticipate that AgentLAB will serve as a valuable benchmark for tracking progress on securing LLM agents in practical settings. The benchmark is publicly available at https://tanqiujiang.github.io/AgentLAB_main.

Related papers

• AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent [53.82005364479556]
  Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities.<n>Existing safety mechanisms mainly rely on external guardrails.<n>We propose AgentLens, a white-box defense framework that performs runtime safety detection and representation-level mitigation.
  arXiv  Detail & Related papers  (2026-06-21T21:13:55Z)
• MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory [12.959058053467075]
  Large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks.<n>They face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives in single-turn settings.<n>We present MAGE, a novel defensive framework designed to counter a wide range of long-horizon threats.
  arXiv  Detail & Related papers  (2026-05-04T23:46:19Z)
• Targeted Bit-Flip Attacks on LLM-Based Agents [9.963281296730896]
  This work introduces Flip-Agent, the first targeted bit-flip attack framework for LLM-based agents.<n>Our experiments show that Flip-Agent significantly outperforms existing targeted BFAs on real-world agent tasks.
  arXiv  Detail & Related papers  (2026-03-07T04:57:49Z)
• AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification [25.817251923574286]
  We propose a novel inference-time detection and mitigation framework for large language model (LLM) agents.<n>AgentSentry is the first inference-time defense to model multi-turn IPI as a temporal causal takeover.<n>We evaluate AgentSentry on the textscAgentDojo benchmark across four task suites, three IPI attack families, and multiple black-box LLMs.
  arXiv  Detail & Related papers  (2026-02-26T07:59:10Z)
• Adversarial Reinforcement Learning for Large Language Model Agent Safety [20.704989548285372]
  Large Language Model (LLM) agents can leverage tools like Google Search to complete complex tasks.<n>Current defense strategies rely on fine-tuning LLM agents on datasets of known attacks.<n>We propose Adversarial Reinforcement Learning for Agent Safety (ARLAS), a novel framework that leverages adversarial reinforcement learning (RL) by formulating the problem as a two-player zero-sum game.
  arXiv  Detail & Related papers  (2025-10-06T23:09:18Z)
• PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents [60.23552141928126]
  PSG-Agent is a personalized and dynamic system for LLM-based agents.<n>First, PSG-Agent creates personalized guardrails by mining the interaction history for stable traits.<n>Second, PSG-Agent implements continuous monitoring across the agent pipeline with specialized guards.
  arXiv  Detail & Related papers  (2025-09-28T03:31:59Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks [88.84977282952602]
  A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs)<n>In this paper, we analyze security and privacy vulnerabilities that are unique to LLM agents.<n>We conduct a series of illustrative attacks on popular open-source and commercial agents, demonstrating the immediate practical implications of their vulnerabilities.
  arXiv  Detail & Related papers  (2025-02-12T17:19:36Z)
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents [84.96249955105777]
  LLM agents may pose a greater risk if misused, but their robustness remains underexplored.<n>We propose a new benchmark called AgentHarm to facilitate research on LLM agent misuse.<n>We find leading LLMs are surprisingly compliant with malicious agent requests without jailbreaking.
  arXiv  Detail & Related papers  (2024-10-11T17:39:22Z)
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents [27.701301913159067]
  We introduce AgentDojo, an evaluation framework for agents that execute tools over untrusted data. AgentDojo is not a static test suite, but rather an environment for designing and evaluating new agent tasks, defenses, and adaptive attacks. We populate AgentDojo with 97 realistic tasks, 629 security test cases, and various attack and defense paradigms from the literature.
  arXiv  Detail & Related papers  (2024-06-19T08:55:56Z)
• AgentBench: Evaluating LLMs as Agents [99.12825098528212]
  Large Language Model (LLM) as agents has been widely acknowledged recently.<n>We present AgentBench, a benchmark that consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
  arXiv  Detail & Related papers  (2023-08-07T16:08:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.