RESEARCH · RESEARCH · #2980
Capability‑Grounded Agentic Planning (CGAP) — PDDL-based planning for LLM agents (arXiv:2610.41040v1)
arXiv:2610.41040v1 introduces Capability‑Grounded Agentic Planning (CGAP), which deterministically compiles a tool catalog into an abstract PDDL model, uses an LLM to convert a natural‑language request into goals, and solves the model with a classical planner to produce multi-step plans; at runtime an LLM fills in entity-specific tool calls and deterministic checks plus an LLM verifier ensure requested results meet the original request. In experiments with three LLMs on ToolSandbox, ComplexFuncBench, BFCL multi-turn, and tau^2-bench retail, CGAP outperformed a standard tool-calling agent by up to 28.9 points.
KEY POINTS
- arXiv:2610.41040v1 introduces Capability‑Grounded Agentic Planning (CGAP), which deterministically compiles a tool catalog into an abstract PDDL model, uses an LLM to convert a natural‑language request into goals, and solves the model with a classical planner to produce multi-step plans; at runtime an LLM fills in entity-specific tool calls and deterministic checks plus an LLM verifier ensure requested results meet the original request.
- In experiments with three LLMs on ToolSandbox, ComplexFuncBench, BFCL multi-turn, and tau^2-bench retail, CGAP outperformed a standard tool-calling agent by up to 28.9 points.
- CGAP combines symbolic planning with LLM goal generation and verification to produce more reliable, executable multi-step tool plans for LLM agents, improving multi-call task performance.
WHY IT MATTERS
CGAP combines symbolic planning with LLM goal generation and verification to produce more reliable, executable multi-step tool plans for LLM agents, improving multi-call task performance.