Research map / Large language models / Reasoning and chain of thought
Language Models can Solve Computer Tasks
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 |
|---|---|---|---|
| Add RCI to zero-shot prompting | gpt-3.5-turbo · GSM8K | accuracy: 77.95 -> 85.43 | Helped |
| Add RCI to zero-shot prompting | gpt-3.5-turbo · MultiArith | accuracy: 94.48 -> 97.64 | Helped |
| Add RCI to zero-shot prompting | gpt-3.5-turbo · AddSub | accuracy: 88.58 -> 89.76 | Helped |
| Add RCI to zero-shot prompting | gpt-3.5-turbo · SVAMP | accuracy: 80.70 -> 84.65 | Helped |
| Add RCI to zero-shot prompting | gpt-3.5-turbo · SingleEq | accuracy: 86.61 -> 94.49 | Helped |
| Add RCI to zero-shot prompting | gpt-3.5-turbo · AQuA | accuracy: 60.23 -> 67.32 | Helped |
| Add RCI to zero-shot prompting | gpt-3.5-turbo · CommonSenseQA | accuracy: 64.56 -> 68.11 | Helped |
| Add RCI to zero-shot prompting | gpt-3.5-turbo · StrategyQA | accuracy: 48.81 -> 61.81 | Helped |
| Add RCI to Zero-Shot CoT | gpt-3.5-turbo · GSM8K | accuracy: 82.28 -> 86.22 | Helped |
| Add RCI to Few-Shot CoT | gpt-3.5-turbo · MultiArith | accuracy: 98.82 -> 99.21 | Helped |
| Add RCI to Few-Shot CoT | gpt-3.5-turbo · AddSub | accuracy: 89.37 -> 90.55 | Helped |
| Add RCI to Few-Shot CoT | gpt-3.5-turbo · SVAMP | accuracy: 83.46 -> 87.40 | Helped |
Closest papers by meaning
- Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models (ICML 2024 · similarity 0.89)
- Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysis (AAAI 2024 · similarity 0.89)
- StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving (NeurIPS 2024 · similarity 0.88)
- Self-Challenging Language Model Agents (NeurIPS 2025 · similarity 0.88)
- THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS (ICLR 2024 · similarity 0.88)
- Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL (NeurIPS 2025 · similarity 0.88)
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.