[Submitted on 25 Mar 2026 (v1), last revised 21 Oct 2026 (this version, v4)]
Abstract:Recent work provides overwhelming evidence that LLMs, even those trained to scale their reasoning trace, quickly deteriorate at planning as problems become more complex. LLM-as-Formalizers aim to address this by employing LLMs as a bridge to translate natural language descriptions into structured planning representations such as PDDL, which are then fed to a programmatic solver. We observe that its success may be overstated because planning problem descriptions in standard benchmarks often have a one-to-one mapping to PDDL, which departs from real use cases. To address this, we introduce the notion of unraveling problems where a natural yet succinct description translates into a very large PDDL representation. Using unraveling variants of four standard planning domains, we demonstrate that LLM Formalizers also do not always scale. We tackle this challenge by introducing a new paradigm, LLM-as-Higher-Order-Formalizer, where the LLM generates a high-level program that captures the recurrent logic within the description and in turn generates the larger PDDL representation. This decouples token output from the combinatorial explosion of the underlying formalization and search space, leading to improved performance for complex problems.
Submission history
From: Owen Jiang [view email]
[v1] Wed, 25 Mar 2026 02:01:09 UTC (4,533 KB)
[v2] Sat, 4 Jul 2026 18:41:30 UTC (7,496 KB)
[v3] Fri, 16 Oct 2026 23:42:04 UTC (6,754 KB)
[v4] Wed, 21 Oct 2026 18:46:01 UTC (6,754 KB)
