arXiv cs.CL· Shikha Shrestha, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik·· 11 小时前AI 评分46
CGAP：基于能力约束的智能体规划方法
Capability-Grounded Agentic Planning
AI 导读
研究者提出 Capability-Grounded Agentic Planning（CGAP），将工具目录确定性编译为 PDDL 模型，由 LLM 把请求转成目标后交给经典规划器求解，避免试错式工具调用。
正文 · 原文
Abstract:LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls. Typically, the LLM picks these calls by trial and error, with no guarantee of an executable plan. We present Capability-Grounded Agentic Planning (CGAP), which instead reasons about what a request requires and what tools provide. CGAP compiles the tool catalog deterministically into a PDDL model, uses an LLM to turn the request into goals, and solves the model with a classical planner. Since tool outputs are unknown in advance, the model is abstract, tracking which inputs are available, not their values. During execution, an LLM adds entity-specific calls that abstract plans omit, and deterministic checks reject any that break the plan. Every argument is drawn from a cited source, such as a conversation span or an earlier tool response, and each requested result counts as delivered only after an LLM verifier checks it against the request. With three LLMs on ToolSandbox, ComplexFuncBench, BFCL multi-turn, and $\tau^2$-bench retail, CGAP outperforms a standard tool-calling agent by up to 28.9 points.
| Comments: | 25 pages, 3 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.41040 [cs.AI] |
| (or arXiv:2610.41040v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41040 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shikha Shrestha [view email]
[v1]
Thu, 29 Oct 2026 22:32:01 UTC (265 KB)
来源：arXiv cs.CL · arxiv.org