Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
Mugeng Liu, Shuoqi Li, Yixuan Zhang, Yun Ma
摘要
In the agentic web era, LLM-based agents increasingly invoke web services as tools, yet most interfaces remain static endpoints that poorly express long-horizon workflows with loops, conditionals, joins, and retries. We present ToolPro, which represents an agent's tool intent as an executable tool program that compactly encodes multi-step service interactions with explicit effect types. ToolPro combines constraint-guided program construction, effect-aware replay for exactly-once state-modifying calls, and a profile-driven policy that decides when program execution outperforms stepwise calling. We instantiate ToolPro over MCP-style services with WebAssembly sandboxing and evaluate it on diverse workflows of real-world applications. ToolPro reduces end-to-end latency by up to 53.4% and client-side traffic by up to 96.1%, with larger gains under higher network latency and workflow complexity.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper12
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu 等NeurIPS 2023 · 被引用 5,989 次
- WebShop: Towards Scalable Real-World Web Interaction with Grounded Language AgentsShunyu Yao, Howard Chen, John Yang, Karthik NarasimhanNeurIPS 2022 · 被引用 1,477 次
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsYujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu 等ICLR 2024 · 被引用 1,469 次
- WebArena: A Realistic Web Environment for Building Autonomous AgentsShuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou 等ICLR 2024 · 被引用 1,197 次
- AgentBench: Evaluating LLMs as AgentsXiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu 等ICLR 2024 · 被引用 748 次
相关 Paper
- Agent JIT Compilation for Latency-Optimizing Web Agent Planning and SchedulingCaleb Winston, Ron Yifeng Wang, Azalia Mirhoseini, Christoforos KozyrakisICML 2026
- Parallelizing LLM Agent Execution with Contrastive Task AllocationYuyang Peng, Yanling Xu, Shuyi Wang, Xiaofei Liao 等KDD 2026 · 被引用 1 次
- Tool-Star: Empowering Multi-Tool Collaborative Web Agent via Reinforcement LearningGuanting Dong, Yifei Chen, Xiaoxi Li, Jiajie Jin 等SIGIR 2026 · 被引用 1 次
- MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM AgentsDongsen Zhang, Zekun Li, Xu Luo, Xuannan Liu 等ICLR 2026 · 被引用 47 次
- AgentVocab: Structure-Aware Vocabulary Adaptation for Efficient LLM AgentsKai Bian, Haosi Mo, Xuebo Liu, Shuangyong Song 等ICML 2026
