LAPI(S)²: Language to Action Planning via Iterative Schema Synthesis

Translating natural language into executable plans is a provably complex problem. LLMs can generate syntactically valid PDDL, which is prone to contain semantic errors. Current state-of-the-art systems tend to bypass this issue, by relying on pre-defined ground-truth domains, or skipping structural validation altogether, trusting the LLM’s own self-consistency. To bridge this gap, we introduce LAPI(S)². Our system uses symbolic and semantic checks to iteratively improve the generated symbolic domains, guaranteeing the successful execution of resulting plans in ground-truth scenarios. We tested LAPI(S)² on seven standard International Planning Competition (IPC) domains against baselines like LLM+P and NL2Plan. Zero-shot self-consistency improves by +29% over LLM+P. Most importantly, an average success rate of 73% is achieved for plans in real simulators, while the baselines failed completely with a 0% success rate. Demo website: https://emanuelemusumeci.github.io/LAPIS/, Video: https://www.youtube.com/watch?v=rDj76jpD9g4