Cover Image

Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qiu, Jiyang, Ma, Xinbei, Xu, Yunqing, Zhang, Zhuosheng, Zhao, Hai
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MEGen: Generative Backdoor into Large Language Models via Model Editing
by: Qiu, Jiyang, et al.
Published: (2024)

Plan-over-Graph: Towards Parallelable LLM Agent Schedule
by: Zhang, Shiqi, et al.
Published: (2025)

Textual-to-Visual Iterative Self-Verification for Slide Generation
by: Xu, Yunqing, et al.
Published: (2025)

ParaCook: On Time-Efficient Planning for Multi-Agent Systems
by: Zhang, Shiqi, et al.
Published: (2025)

Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering
by: Wu, Yexin, et al.
Published: (2024)

On the Robustness of Editing Large Language Models
by: Ma, Xinbei, et al.
Published: (2024)

Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models
by: Zou, Anni, et al.
Published: (2023)

Dynamic Planning for LLM-based Graphical User Interface Automation
by: Zhang, Shaoqing, et al.
Published: (2024)

CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation
by: Ma, Xinbei, et al.
Published: (2024)

An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains
by: Yan, Zihe, et al.
Published: (2025)

The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms
by: Shehata, Dahlia, et al.
Published: (2026)

AgenticData: An Agentic Data Analytics System for Heterogeneous Data
by: Sun, Ji, et al.
Published: (2025)

MedDCR: Learning to Design Agentic Workflows for Medical Coding
by: Zheng, Jiyang, et al.
Published: (2025)

Automating Supply Chain Disruption Monitoring via an Agentic AI Approach
by: AlMahri, Sara, et al.
Published: (2026)

Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
by: Wu, Junde, et al.
Published: (2025)

MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
by: Ning, Xuying, et al.
Published: (2026)

AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation
by: Liu, Xianyang, et al.
Published: (2025)

Multimodal Chain-of-Thought Reasoning in Language Models
by: Zhang, Zhuosheng, et al.
Published: (2023)

You Only Look at Screens: Multimodal Chain-of-Action Agents
by: Zhang, Zhuosheng, et al.
Published: (2023)

PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization
by: Cao, Zouying, et al.
Published: (2025)

Self-Prompting Large Language Models for Zero-Shot Open-Domain QA
by: Li, Junlong, et al.
Published: (2022)

Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
by: Lin, Chenhao, et al.
Published: (2025)

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
by: Wang, Yixu, et al.
Published: (2025)

VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining
by: Zhu, Xuanyu, et al.
Published: (2026)

No-Human in the Loop: Agentic Evaluation at Scale for Recommendation
by: Zhang, Tao, et al.
Published: (2025)

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
by: Wu, Zongru, et al.
Published: (2024)

Aggregation Queries over Unstructured Text: Benchmark and Agentic Method
by: Zhu, Haojia, et al.
Published: (2026)

SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence
by: Zhang, Yao, et al.
Published: (2025)

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
by: Bullwinkel, Blake, et al.
Published: (2026)

The Auton Agentic AI Framework
by: Cao, Sheng, et al.
Published: (2026)

Agentic Uncertainty Reveals Agentic Overconfidence
by: Kaddour, Jean, et al.
Published: (2026)

CodeCompass: Navigating the Navigation Paradox in Agentic Code Intelligence
by: Paipuru, Tarakanath
Published: (2026)

Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
by: Wei, Qianshan, et al.
Published: (2026)

JudgeFlow: Agentic Workflow Optimization via Block Judge
by: Ma, Zihan, et al.
Published: (2026)

Agentic AI Sustainability Assessment for Supply Chain Document Insights
by: Gosmar, Diego, et al.
Published: (2025)

Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking
by: Jannelli, Valeria, et al.
Published: (2024)

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
by: Zhao, Shuai, et al.
Published: (2023)

Verifiable Process Rewards for Agentic Reasoning
by: Yuan, Huining, et al.
Published: (2026)

Skill Reuse as Compression in Agentic RL
by: Xu, Zhikun, et al.
Published: (2026)

ADR: An Agentic Detection System for Enterprise Agentic AI Security
by: Li, Chenning, et al.
Published: (2026)