Automating Thought of Search: A Journey Towards Soundness and Completeness

ICLR 2026 Conference Submission18270 Authors

Keywords: Thought of Search, planning with language models

TL;DR: We introduce AutoToS, a significant step toward automating Thought of Search. By guiding LLMs with unit-test feedback, AutoToS generates sound search components and achieves 100% accuracy across evaluated domains with few LLM calls

Abstract:

Large language models (LLMs) are being used to solve planning problems that require search. Most of the literature uses LLMs as world models to define the search space, forgoing soundness for the sake of flexibility. A recent work, Thought of Search (ToS), proposed defining the search space with code, having LLMs produce that code. ToS requires a _human in the loop_, collaboratively producing a sound successor function and goal test. The result, however, is worth the effort: all the tested datasets were solved with 100% accuracy.
Consequently, there is great potential to automate the ToS process.
We take a first major step towards automating ToS (AutoToS), taking the _human out of the loop_ of interactions with the language model. AutoToS guides the language model step by step towards the generation of sound and complete search components, through feedback from both generic and domain specific unit tests.
We show that AutoToS is able to achieve 100% accuracy on all the evaluated domains with a small number of LLM calls.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 18270