Research map / Large language models / Reasoning and chain of thought
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| ToT search instead of CoT | GPT-4 · Game of 24 | success rate: 4.0% -> 74% | Helped |
| increase BFS breadth 1 -> 5 (ablation) | ToT · Game of 24 | success rate: 45% -> 74% | Helped |
| ToT plan voting instead of CoT | GPT-4 · Creative Writing | coherency score: 6.93 -> 7.56 | Helped |
| add backtracking (ablation) | ToT · 5x5 Crosswords | word-level success: 20% -> 60% | Helped |
| add state-evaluation pruning (ablation) | ToT DFS · 5x5 Crosswords | success | Helped |
| ToT instead of CoT | GPT-4 · GSM8K / StrategyQA | accuracy | Helped |
| weaker generator (GPT-3.5) vs weaker evaluator (ablation) | ToT · Game of 24 | success rate: 74% -> 31% (gen) / 64% (eval) | Hurt |
| add iterative refine | ToT · Creative Writing | coherency score: 7.56 -> 7.91 | Helped |
Closest papers by meaning
- Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models (ICLR 2024 · similarity 0.91)
- Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning (ICML 2025 · similarity 0.90)
- Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models (ICML 2024 · similarity 0.90)
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models (AAAI 2024 · similarity 0.90)
- THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS (ICLR 2024 · similarity 0.90)
- Toward Adaptive Reasoning in Large Language Models with Thought Rollback (ICML 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.