AIR: Improving Agent Safety through Incident Response

• URL: http://arxiv.org/abs/2602.11749v1
• Date: Thu, 12 Feb 2026 09:24:50 GMT
• Title: AIR: Improving Agent Safety through Incident Response
• Abstract summary: We introduce AIR, the first incident response framework for Large Language Model (LLM) agent systems.<n> AIR defines a domain-specific language for managing the incident response lifecycle autonomously in LLM agent systems.<n>Results show that AIR achieves detection, remediation, and eradication success rates all exceeding 90%.
• Score: 8.845095096023021
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Model (LLM) agents are increasingly deployed in practice across a wide range of autonomous applications. Yet current safety mechanisms for LLM agents focus almost exclusively on preventing failures in advance, providing limited capabilities for responding to, containing, or recovering from incidents after they inevitably arise. In this work, we introduce AIR, the first incident response framework for LLM agent systems. AIR defines a domain-specific language for managing the incident response lifecycle autonomously in LLM agent systems, and integrates it into the agent's execution loop to (1) detect incidents via semantic checks grounded in the current environment state and recent context, (2) guide the agent to execute containment and recovery actions via its tools, and (3) synthesize guardrail rules during eradication to block similar incidents in future executions. We evaluate AIR on three representative agent types. Results show that AIR achieves detection, remediation, and eradication success rates all exceeding 90%. Extensive experiments further confirm the necessity of AIR's key design components, show the timeliness and moderate overhead of AIR, and demonstrate that LLM-generated rules can approach the effectiveness of developer-authored rules across domains. These results show that incident response is both feasible and essential as a first-class mechanism for improving agent safety.

Related papers

• Towards Risk-free AI Agent Deployment [13.502827903528948]
  We argue that risk-free deployment must be grounded in the agent's trajectory.<n>This article begins with the challenges of testing agents, including the oracle problem.<n>We distill these directions into a practical deployment-readiness checklist.
  arXiv  Detail & Related papers  (2026-08-17T11:07:07Z)
• 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)
• SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems [31.635133844217318]
  LLM-based multi-agent systems (MAS) solve complex tasks through inter-agent collaboration, but their communication-driven nature allows security risks to spread across agents and trigger system-wide failures.<n>We propose a proactive defense framework for MAS security, namely a Simulation-aware Interception Guard (SAIGuard)<n>SAIGuard performs communication-state simulation over the MAS interaction graph, estimates the impact of incoming messages on local agent states and the global MAS state, and detects risky messages via reconstruction deviations from benign communication patterns.
  arXiv  Detail & Related papers  (2026-06-10T05:37:58Z)
• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments [26.85543164204341]
  behavior jailbreak is where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences.<n>Existing benchmarks either evaluate safety at the semantic layer alone, missing physical-layer harms, or fail to isolate test cases.<n>We present LITMUS, a benchmark addressing both gaps via a semantic-physical dual verification mechanism and OS-level state rollback.
  arXiv  Detail & Related papers  (2026-05-11T16:14:04Z)
• FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments [60.3427704389541]
  Large Language Models are being increasingly deployed as the decision-making core of autonomous agents.<n>Yet, in conversational benchmarks, these agents frequently fail due to the cascading effects of incorrect decision-making.<n>We present the Failure-Aware Meta-Agentic framework to tackle these challenges.
  arXiv  Detail & Related papers  (2026-04-28T02:21:53Z)
• 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)
• ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction [24.416258744287166]
  ICON is a probing-to-mitigation framework that neutralizes attacks while preserving task continuity.<n>ICON achieves a competitive 0.4% ASR, matching commercial grade detectors, while yielding a over 50% task utility gain.
  arXiv  Detail & Related papers  (2026-02-24T09:13:05Z)
• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security [126.49733412191416]
  Current guardrail models lack agentic risk awareness and transparency in risk diagnosis.<n>We propose a unified three-dimensional taxonomy that categorizes agentic risks by their source (where), failure mode (how), and consequence (what)<n>We introduce a new fine-grained agentic safety benchmark (ATBench) and a Diagnostic Guardrail framework for agent safety and security (AgentDoG)
  arXiv  Detail & Related papers  (2026-01-26T13:45:41Z)
• The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check [54.08619694620588]
  We present a comprehensive evaluation of dLLMs across two distinct agentic paradigms: Embodied Agents and Tool-Calling Agents.<n>Our results on Agentboard and BFCL reveal a "bitter lesson": current dLLMs fail to serve as reliable agentic backbones.
  arXiv  Detail & Related papers  (2026-01-19T11:45:39Z)
• ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback [53.2744585868162]
  Monitoring step-level tool invocation behaviors in real time is critical for agent deployment.<n>We first construct TS-Bench, a novel benchmark for step-level tool invocation safety detection in LLM agents.<n>We then develop a guardrail model, TS-Guard, using multi-task reinforcement learning.
  arXiv  Detail & Related papers  (2026-01-15T07:54:32Z)
• Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning [89.1856483797116]
  We introduce BEAT, the first framework to inject visual backdoors into MLLM-based embodied agents.<n>Unlike textual triggers, object triggers exhibit wide variation across viewpoints and lighting, making them difficult to implant reliably.<n>BEAT achieves attack success rates up to 80%, while maintaining strong benign task performance.
  arXiv  Detail & Related papers  (2025-10-31T16:50:49Z)
• Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval [49.85856484781787]
  We introduce Interact-RAG, a new paradigm that elevates the LLM agent into an active manipulator of the retrieval process.<n>We develop a reasoning-enhanced workflow, which enables both zero-shot execution and the synthesis of interaction trajectories.<n>Experiments across six benchmarks demonstrate that Interact-RAG significantly outperforms other advanced methods.
  arXiv  Detail & Related papers  (2025-10-31T15:48:43Z)
• Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety [2.7030665672026846]
  Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences.<n>We propose using "quitting" as a simple yet effective behavioral mechanism for LLM agents to recognize and withdraw from situations where they lack confidence.
  arXiv  Detail & Related papers  (2025-10-18T13:22:19Z)
• AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning [78.5751183537704]
  AdvEvo-MARL is a co-evolutionary multi-agent reinforcement learning framework that internalizes safety into task agents.<n>Rather than relying on external guards, AdvEvo-MARL jointly optimize attackers and defenders.
  arXiv  Detail & Related papers  (2025-10-02T02:06:30Z)
• 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)
• AgentGuard: Repurposing Agentic Orchestrator for Safety Evaluation of Tool Orchestration [0.3222802562733787]
  AgentGuard is a framework to autonomously discover and validate unsafe tool-use.<n>It generates safety constraints to confine the behaviors of agents, achieving the baseline of safety guarantee.<n>The framework operates through four phases: identifying unsafe, validating them in real-world execution, generating safety constraints, and validating constraint efficacy.
  arXiv  Detail & Related papers  (2025-02-13T23:00:33Z)
• Towards Action Hijacking of Large Language Model-based Agent [23.13653350521422]
  We introduce AI$mathbf2$, a novel attack to manipulate the action plans of LLM-based applications.<n>It first collects action-aware knowledge from the victim application.<n>Based on such knowledge, the attacker can generate misleading input, which can mislead the LLM to generate harmful action plans.
  arXiv  Detail & Related papers  (2024-12-14T12:11:26Z)

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.