Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 14 of its 30 references that are in the map. First posted on arXiv 18 Jun 2026.
Builds on
14 of 30 references.
Closest ancestors · 2
Same direction, newest first
- 2024AFlow: Automating Agentic Workflow Generation14 Oct
- 2024Executable Code Actions Elicit Better LLM Agents1 Feb
Other references · 12
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
- 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
- 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
- 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
- 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
- 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 124
- 2024Beyond Browsing: API-Based Web Agentscited by 78
- 2024ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agentscited by 36
- 2024Research on WebAssembly Runtimes: A Surveycited by 2
- 2025WebANNS: Fast and Efficient Approximate Nearest Neighbor Search in Web Browserscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows
- 2026GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
- 2026The World Won't Stay Still: Programmable Evolution for Agent Benchmarks
- 2025NetGent: Agent-Based Automation of Network Application Workflows
- 2026Agentic AI Workload Characteristics
- 2026From Tool Orchestration to Code Execution: A Study of MCP Design Choices
- 2026The Tool Illusion: Rethinking Tool Use in Web Agents
- 2026Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction