Research map / Large language models / Agents, code and math
HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design
ChentongChen, Mengyuan Zhong, Jialong Shi, Jianyong Sun, Ye Fan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 the Insight Pool (hindsight) (ablation) | HiFo-Prompt · TSP100 | gap: 16.26% -> 8.58% | Improved |
| add the Navigator (foresight) (ablation) | HiFo-Prompt · TSP100 | gap: 11.48% -> 8.58% | Improved |
| add both Insight Pool and Navigator (ablation) | HiFo-Prompt · TSP100 | gap: 18.80% -> 8.58% | Improved |
| add the Insight Pool (hindsight) (ablation) | HiFo-Prompt · TSP20 | gap: 11.07% -> 3.62% | Improved |
| add the Navigator (foresight) (ablation) | HiFo-Prompt · TSP50 | gap: 10.31% -> 6.63% | Improved |
| add the Insight Pool (hindsight) (ablation) | HiFo-Prompt · Online BPP 5k, 100 | gap: 1.27% -> 0.69% | Improved |
| add the Navigator (foresight) (ablation) | HiFo-Prompt · Online BPP 5k, 100 | gap: 1.26% -> 0.69% | Improved |
| add both components (ablation) | HiFo-Prompt · Online BPP 5k, 100 | gap: 2.19% -> 0.69% | Improved |
| add the Navigator (foresight) (ablation) | HiFo-Prompt · Online BPP 1k, 100 | gap: 2.83% -> 2.19% | Improved |
| add the Insight Pool (hindsight) (ablation) | HiFo-Prompt · Online BPP 1k, 100 | gap: 4.33% -> 2.19% | Improved |
| use HiFo-Prompt instead of EoH | LLM heuristic design · TSP50 step-by-step | gap: 12.820% -> 6.625% | Improved |
| use HiFo-Prompt instead of MCTS-AHD | LLM heuristic design · TSP200 step-by-step | gap: 13.510% -> 8.877% | Improved |
Closest papers by meaning
- HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs (AAAI 2025 · similarity 0.88)
- PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs (ICML 2026 · similarity 0.87)
- ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution (NeurIPS 2024 · similarity 0.86)
- SayCanPay: Heuristic Planning with Large Language Models Using Learnable Domain Knowledge (AAAI 2024 · similarity 0.86)
- Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design (ICML 2025 · similarity 0.86)
- Automated Creation of Reusable and Diverse Toolsets for Enhancing LLM Reasoning (AAAI 2025 · similarity 0.86)
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.
