Cover Image

The Tool Illusion: Rethinking Tool Use in Web Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lou, Renze, Peng, Baolin, Yao, Wenlin, Wu, Qianhui, Cheng, Hao, Nath, Suman, Yin, Wenpeng, Gao, Jianfeng
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Toward Zero-Shot Instruction Following
by: Lou, Renze, et al.
Published: (2023)

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
by: Yang, Rui, et al.
Published: (2026)

WebXSkill: Skill Learning for Autonomous Web Agents
by: Wang, Zhaoyang, et al.
Published: (2026)

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
by: Yu, Xiao, et al.
Published: (2025)

Large Language Model Instruction Following: A Survey of Progresses and Challenges
by: Lou, Renze, et al.
Published: (2023)

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
by: Yu, Xiao, et al.
Published: (2025)

SynthAgent: Adapting Web Agents with Synthetic Supervision
by: Wang, Zhaoyang, et al.
Published: (2025)

Large Language Models for Mathematical Reasoning: Progresses and Challenges
by: Ahn, Janice, et al.
Published: (2024)

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
by: Yang, Rui, et al.
Published: (2026)

Synthetic Computers at Scale for Long-Horizon Productivity Simulation
by: Ge, Tao, et al.
Published: (2026)

AutoSurfer -- Teaching Web Agents through Comprehensive Surfing, Learning, and Modeling
by: Faisal, Fazle Elahi, et al.
Published: (2026)

Orchard: An Open-Source Agentic Modeling Framework
by: Peng, Baolin, et al.
Published: (2026)

Learning to Use Tools via Cooperative and Interactive Agents
by: Shi, Zhengliang, et al.
Published: (2024)

ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
by: Yu, Xiao, et al.
Published: (2024)

Reinforcement World Model Learning for LLM-based Agents
by: Yu, Xiao, et al.
Published: (2026)

Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
by: Shi, Zhengliang, et al.
Published: (2024)

Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges
by: Wang, Hongru, et al.
Published: (2025)

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
by: Lou, Renze, et al.
Published: (2023)

ToolComp: A Multi-Tool Reasoning & Process Supervision Benchmark
by: Nath, Vaskar, et al.
Published: (2025)

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

LLMs' Classification Performance is Overclaimed
by: Xu, Hanzi, et al.
Published: (2024)

GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning
by: Wu, Jiaqi, et al.
Published: (2025)

ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
by: Liu, Marianne Menglin, et al.
Published: (2025)

MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
by: Huang, Yue, et al.
Published: (2023)

Teaching Language Models to Self-Improve through Interactive Demonstrations
by: Yu, Xiao, et al.
Published: (2023)

Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models
by: Li, Miaoran, et al.
Published: (2023)

An Illusion of Progress? Assessing the Current State of Web Agents
by: Xue, Tianci, et al.
Published: (2025)

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
by: Chen, Yongchao, et al.
Published: (2025)

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
by: Renze, Matthew, et al.
Published: (2024)

WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
by: Wei, Zhepei, et al.
Published: (2025)

The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents
by: Xuan, Weihao, et al.
Published: (2026)

FamilyTool: A Multi-hop Personalized Tool Use Benchmark
by: Wang, Yuxin, et al.
Published: (2025)

FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
by: Huang, Caishuang, et al.
Published: (2026)

MMedAgent: Learning to Use Medical Tools with Multi-modal Agent
by: Li, Binxu, et al.
Published: (2024)

Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems
by: Lumer, Elias, et al.
Published: (2025)

TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training
by: Yang, Jinluan, et al.
Published: (2026)

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
by: He, Hongliang, et al.
Published: (2024)

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
by: Chen, Shiqi, et al.
Published: (2026)

Efficient Tool Use with Chain-of-Abstraction Reasoning
by: Gao, Silin, et al.
Published: (2024)

GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
by: Wang, Jize, et al.
Published: (2026)