The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents
Source
Bo Yan, Weikai Lin, Song Wang
Author
Bo Yan, Weikai Lin, Song Wang
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Building AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → tool menus around a pre-execution 'state path' rather than pure relevance ranking raises online task success on ToolBench from 73.7% to 89.8% by ensuring prerequisite tools are surfaced before the final action.
Key quotes
“We introduce the state path, a pre-execution route from the observable request state to the desired outcome, and propose State-Path Tool Menu to learn it.”
“On ToolBench, our menu raises online success from 0.737 to 0.898 and outperforms retrieval, reranking, generation, and routing baselines without changing the agent.”
“The State-Path menu also covers more complete chains with 32 tools than the official list covers with 128, and its success gain persists across executor families with different model capacities.”
articleHarness Engineering in LLM Tool Use via Agent-Native Reusable Tool PrimitivesHaibo Jin, Suijin Wang, Xucheng Yu, Haojing Luo, Haohan Wang
articleHxAgent: Iterative Agent Planning for End-to-End Web Application TestingTu Nguyen, Duy Cao, Viet Nguyen, Phu Nguyen, Vy Le, Nguyen TK Nguyen, Tien N. Nguyen, Vu Nguyen
articleThe Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent BehaviorXiangzhe Xu, Hamidreza Saghir, Qianhui Wu, Marc-Alexandre C\^ot\'e, Tong Wang, Kiran Lakkaraju, Kexin Pei, Xiangyu Zhang