paper-with-me

홈 › Papers

Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning

2026-05-07 · Leon Hamm, Zlatan Ajanovic arxiv

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 metric can then be used to prune branches and reduce the scope of the search. Although this method introduces more prompts per state, the overall token cost can be reduced by pruning and reducing the overall tree size. This procedure is tested and compared using several benchmarks in language-based planning and general reasoning.

📄 PDF Abstract BibTeX arXiv:2605.06040

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningGeneral Knowledge

Similar Papers 제목 키워드 기반

ToC: Tree-of-Claims Search with Multi-Agent Language Models

2025-11-21 · Shuyang Yu, Jianan Liang, Hui Hu arxiv

Optimizing patent claims is a critical yet challenging task, demanding careful balance between maximizing novelty and preserving legal scope. Manual claim drafting is labor-intensive, costly, and inherently inconsistent,…

Depth-Bounded Epistemic Planning

2024-06-03 · Thomas Bolander, Alessandro Burigana, Marco Montali

In this paper, we propose a novel algorithm for epistemic planning based on dynamic epistemic logic (DEL). The novelty is that we limit the depth of reasoning of the planning agent to an upper bound b, meaning that the p…

Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Search

2025-10-10 · Kamel Alrashedy, Vriksha Srihari, Zulfiqar Zaidi, Ridam Srivastava 외 arxiv

While researchers have made significant progress in enabling large language models (LLMs) to perform multi-step planning, LLMs struggle to ensure that those plans align with high-level user intent and satisfy symbolic co…

Arithmetic ReasoningCode Generation

Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training

2023-09-29 · Xidong Feng, Ziyu Wan, Muning Wen, Stephen Marcus McAleer 외

Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the reasoning capabilities of LLMs by using tree-search algorithms to guide multi-step reasoning. These methods rely on prompting a …

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model

Policy Guided Tree Search for Enhanced LLM Reasoning

2025-02-04 · Yang Li

Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought prompting and tree search techniques show p…

Mathematical ReasoningNavigate