Research map / Large language models / Agents, code and math
Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery
Xinyi Ke, Kai Li, Junliang Xing, Yifan Zhang, Jian Cheng
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 solver-generator game co-evolution (ASRO) | EoH program search · OBP Hard28-SA | optimality gap (%): 40.02 -> 12.45 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · OBP Falkenauer T | optimality gap (%): 12.11 -> 7.11 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · OBP Weibull (training distribution) | optimality gap (%): 1.56 -> 1.20 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · OBP Hard28-R | optimality gap (%): 8.40 -> 8.06 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · TSPLIB LIB-XL | optimality gap (%): 4.20 -> 3.00 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · TSPLIB LIB-S | optimality gap (%): 0.77 -> 0.21 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · TSP Uniform | optimality gap (%): 0.27 -> 0.05 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · CVRP family M | optimality gap (%): 54.22 -> 22.45 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · CVRP family F | optimality gap (%): 59.78 -> 28.71 | Improved |
| add solver-generator game co-evolution (ASRO) | EoH program search · CVRP family B | optimality gap (%): 12.22 -> 10.49 | Improved |
| add persistent strategy pool and meta-game over data augmentation or memoryless self-play (ablation) | EoH-based baselines · TSPLIB | optimality gap (%) | Improved |
| use LLaMA-3-8B instead of DeepSeek backbone in ASRO-EoH (ablation) | ASRO-EoH · TSPLIB and others | optimality gap (%) | Mixed |
Closest papers by meaning
- HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs (AAAI 2025 · similarity 0.89)
- PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs (ICML 2026 · similarity 0.88)
- ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution (NeurIPS 2024 · similarity 0.87)
- Fleet of Agents: Coordinated Problem Solving with Large Language Models (ICML 2025 · similarity 0.87)
- SayCanPay: Heuristic Planning with Large Language Models Using Learnable Domain Knowledge (AAAI 2024 · similarity 0.87)
- CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization (AAAI 2026 · similarity 0.87)
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.
