Imagen de Portada

Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fan, Flint Xiaofeng, Tan, Cheston, Wattenhofer, Roger, Ong, Yew-Soon
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

Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
por: Fan, Flint Xiaofeng, et al.
Publicado: (2025)

FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
por: Fan, Flint Xiaofeng, et al.
Publicado: (2024)

CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with Screening
por: Mak, Hei Yi, et al.
Publicado: (2024)

A Continuous Encoding-Based Representation for Efficient Multi-Fidelity Multi-Objective Neural Architecture Search
por: Wei, Zhao, et al.
Publicado: (2025)

Automated Large-scale CVRP Solver Design via LLM-assisted Flexible MCTS
por: Guo, Tong, et al.
Publicado: (2026)

Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
por: Jordan, Philip, et al.
Publicado: (2024)

Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity
por: Wan, Zhenglin, et al.
Publicado: (2024)

Multi-Task Learning with Multi-Task Optimization
por: Bai, Lu, et al.
Publicado: (2024)

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
por: Tan, Kim Yong, et al.
Publicado: (2026)

FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
por: Jiang, Wenzheng, et al.
Publicado: (2025)

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
por: Maloyan, Narek, et al.
Publicado: (2026)

Reasoning Effort and Problem Complexity: A Scaling Analysis in LLMs
por: Estermann, Benjamin, et al.
Publicado: (2025)

Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
por: Tan, Kim Yong, et al.
Publicado: (2025)

Distributional Multi-objective Black-box Optimization for Diffusion-model Inference-time Multi-Target Generation
por: Tan, Kim Yong, et al.
Publicado: (2025)

TangramSR: Can Vision-Language Models Reason in Continuous Geometric Space?
por: Zong, Yikun, et al.
Publicado: (2026)

Adaptive In-Context Learning with Large Language Models for Bundle Generation
por: Sun, Zhu, et al.
Publicado: (2023)

GRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimization
por: Zhou, Sihan, et al.
Publicado: (2026)

MRP-LLM: Multitask Reflective Large Language Models for Privacy-Preserving Next POI Recommendation
por: Wu, Ziqing, et al.
Publicado: (2024)

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
por: He, Ping, et al.
Publicado: (2025)

MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark
por: Fan, Shiqing, et al.
Publicado: (2025)

A Simple Yet Effective Approach for Diversified Session-Based Recommendation
por: Yin, Qing, et al.
Publicado: (2024)

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
por: Berdoz, Frédéric, et al.
Publicado: (2024)

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
por: Xie, Yunfei, et al.
Publicado: (2026)

Agentic Spatio-Temporal Grounding via Collaborative Reasoning
por: Zhao, Heng, et al.
Publicado: (2026)

Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction
por: Jiang, Xia, et al.
Publicado: (2026)

Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation
por: Feng, Shanshan, et al.
Publicado: (2024)

The Digital Ecosystem of Beliefs: does evolution favour AI over humans?
por: Bossens, David M., et al.
Publicado: (2024)

SiamNAS: Siamese Surrogate Model for Dominance Relation Prediction in Multi-objective Neural Architecture Search
por: Zhou, Yuyang, et al.
Publicado: (2025)

An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
por: Zhang, Ni, et al.
Publicado: (2025)

MazeMate: An LLM-Powered Chatbot to Support Computational Thinking in Gamified Programming Learning
por: Hou, Chenyu, et al.
Publicado: (2025)

Policy Dispersion in Non-Markovian Environment
por: Qu, Bohao, et al.
Publicado: (2023)

Human-Generative AI Collaborative Problem Solving Who Leads and How Students Perceive the Interactions
por: Zhu, Gaoxia, et al.
Publicado: (2024)

FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol
por: Zhu, Jie, et al.
Publicado: (2026)

Social Learning through Interactions with Other Agents: A Survey
por: Hillier, Dylan, et al.
Publicado: (2024)

Large Language Models can be Guided to Evade AI-Generated Text Detection
por: Lu, Ning, et al.
Publicado: (2023)

AEye: A Visualization Tool for Image Datasets
por: Grötschla, Florian, et al.
Publicado: (2024)

Possibilistic Predictive Uncertainty for Deep Learning
por: Ni, Yao, et al.
Publicado: (2026)

Towards Trustworthy Vital Sign Forecasting: Leveraging Uncertainty for Prediction Intervals
por: Wang, Li Rong, et al.
Publicado: (2025)

Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis
por: Nagar, Aishik, et al.
Publicado: (2024)

Hierarchically Robust Zero-shot Vision-language Models
por: Dong, Junhao, et al.
Publicado: (2026)