Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning
Leon Hamm, Zlatan Ajanovic

TL;DR
This paper introduces a novelty-based tree search method for LLM reasoning that improves efficiency by pruning less unique thoughts, reducing token costs while maintaining reasoning quality.
Contribution
It transfers the concept of novelty from planning to language reasoning, enabling more efficient tree-of-thought search with measurable novelty metrics.
Findings
Reduces overall token costs through pruning based on novelty.
Maintains reasoning performance while decreasing search complexity.
Effective across multiple language reasoning benchmarks.
Abstract
Although advances such as chain-of-thought, tree-of-thought or reinforcement learning have improved the performance of LLMs in reasoning and planning tasks, they are still brittle and have not achieved human-level performance in many domains, and often suffer from high time and token costs. Inspired by the success of width-based search in planning, we explore how the concept of novelty can be transferred to language domains and how it can improve tree-of-thought reasoning. A tree of thoughts relies on building possible "paths" of consecutive ideas or thoughts. These are generated by repeatedly prompting an LLM. In our paper, a measurable concept of novelty is proposed that describes the uniqueness of a new node (thought) in comparison to nodes previously seen in the search tree. Novelty is estimated by prompting an LLM and making use of embedded general knowledge from pre-training. This…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
