Imagen de Portada

Emerging from Ground: Addressing Intent Deviation in Tool-Using Agents via Deriving Real Calls into Virtual Trajectories

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiong, Qian, Huang, Yuekai, Yang, Bo, Zheng, Yujia, Li, Tianhao, Jiang, Ziyou, Chang, Zhiyuan, Li, Zhaoyang, Feng, Huanxiang, Li, Mingyang
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems
por: Xiong, Qian, et al.
Publicado: (2025)

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
por: Chang, Zhiyuan, et al.
Publicado: (2026)

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
por: Jiang, Ziyou, et al.
Publicado: (2025)

All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
por: Jiang, Ziyou, et al.
Publicado: (2026)

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
por: Zheng, Yujia, et al.
Publicado: (2025)

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
por: Chang, Zhiyuan, et al.
Publicado: (2025)

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
por: Wang, Haowei, et al.
Publicado: (2024)

Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
por: Wang, Wenshuo, et al.
Publicado: (2025)

Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents
por: Wang, Ziyi, et al.
Publicado: (2026)

IntentMiner: Intent Inversion Attack via Tool Call Analysis in the Model Context Protocol
por: Yao, Yunhao, et al.
Publicado: (2025)

P‐4.35: Application of Virtual Reality Technology in the Diagnosis and Treatment of Psychological Disorders: An Electroencephalography (EEG)‐Based Approach
por: Weizhi Ma, et al.
Publicado: (2024)

Plant‐Derived Extracellular Vesicles as Potential Emerging Tools for Cancer Therapeutics
por: Lin Ding, et al.
Publicado: (2024)

What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA
por: Chang, Zhiyuan, et al.
Publicado: (2024)

FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks
por: Cao, Yupeng, et al.
Publicado: (2026)

Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
por: Chang, Zhiyuan, et al.
Publicado: (2024)

P‐4.34: Virtual Reality Content Generation for Anxiety and Stress Management: Current Status, Challenges, and Future Developments
por: Yujia Zheng, et al.
Publicado: (2024)

SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety
por: Xu, Zixuan, et al.
Publicado: (2026)

The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
por: Masterman, Tula, et al.
Publicado: (2024)

TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents
por: Gong, Chen, et al.
Publicado: (2024)

Grounding Agent Memory in Contextual Intent
por: Yang, Ruozhen, et al.
Publicado: (2026)

The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
por: Xu, Haoyuan, et al.
Publicado: (2026)

Agentic Link Construction for Environment and Intent Aware 6G Communication
por: Li, Zhaoyang, et al.
Publicado: (2025)

AEGIS: No Tool Call Left Unchecked -- A Pre-Execution Firewall and Audit Layer for AI Agents
por: Yuan, Aojie, et al.
Publicado: (2026)

VulRTex: A Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report
por: Jiang, Ziyou, et al.
Publicado: (2025)

Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue
por: Nuriyev, Mahammad
Publicado: (2025)

W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents
por: Lin, Xiaoqiang, et al.
Publicado: (2026)

ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents
por: Wang, Jiangyuan, et al.
Publicado: (2025)

DroidCall: A Dataset for LLM-powered Android Intent Invocation
por: Xie, Weikai, et al.
Publicado: (2024)

VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
por: Chang, Zhiyuan, et al.
Publicado: (2024)

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
por: Dong, Ben, et al.
Publicado: (2026)

Computing Equilibrium beyond Unilateral Deviation
por: Liu, Mingyang, et al.
Publicado: (2026)

Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests
por: Ning, Jingjie, et al.
Publicado: (2026)

Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling
por: Hooper, Coleman, et al.
Publicado: (2026)

CDKFormer: Contextual Deviation Knowledge-Based Transformer for Long-Tail Trajectory Prediction
por: Lian, Yuansheng, et al.
Publicado: (2025)

Are Agents Probabilistic Automata? A Trace-Based, Memory-Constrained Theory of Agentic AI
por: Koohestani, Roham, et al.
Publicado: (2025)

Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls
por: Zhang, Zeyu, et al.
Publicado: (2026)

AgentStudio: A Toolkit for Building General Virtual Agents
por: Zheng, Longtao, et al.
Publicado: (2024)

Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors
por: Li, Henger, et al.
Publicado: (2025)

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?
por: Li, Xinzhe, et al.
Publicado: (2026)

Data-Enabled Neighboring Extremal: Case Study on Model-Free Trajectory Tracking for Robotic Arm
por: Vahidi-Moghaddam, Amin, et al.
Publicado: (2025)