让大模型策略在对抗游戏中持续进化，突破评估僵局。
Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games
- 让评估者与策略共同进化，动态更新对手池
- 用统计可靠的深度评估替代随机对战得分
- 重点强化最难应对的对手，打破性能瓶颈
大模型驱动的代码进化已实现程序自动发现，但在对抗性多智能体游戏中面临核心挑战：策略提升导致评估环境动态变化，固定评估器失效，进化停滞。本文提出三种机制：评估器共进化（将优胜策略加入对手池）、分层深度评估（以统计可靠结果替代少量对战分数）和弱点压力（动态加权最难对手以突破瓶颈）。这些机制集成于FAMOU框架，基于与OpenEvolve和ShinkaEvolve相同的基座模型代码演化范式。在MCTF 2026 3v3海上夺旗任务中，FAMOU在两种主干LLM下均优于基线，取得最高综合得分（0.526）和对未知对手的最佳泛化能力（61.7%胜率），消融实验验证各机制贡献。值得注意的是，LLM突变过程生成了原始种子策略中完全不存在的战术结构，如前瞻搜索和自适应拦截，证明代码级演化可在对抗场景中催生非平凡算法创新。所生成策略在AAMAS 2026 MCTF竞赛硬件循环赛中获第1名，模拟赛中第3名，验证其真实世界可迁移性。优化实现及评估代码已开源：https://github.com/1xiangliu1/FAMOU-CoEvo
原文摘要 · Abstract (English)
Recent advances in LLM-driven code evolution have enabled automated discovery by iteratively generating and improving programs. However, applying these methods to adversarial multi-agent games introduces a fundamental challenge: the evaluation landscape shifts as strategies improve, causing fixed evaluators to become unreliable and evolution to stagnate. We propose three mechanisms to address this challenge: evaluator co-evolution, which incorporates discovered champions into the opponent pool; hierarchical deep evaluation, which replaces noisy few-game scores with statistically reliable assessments; and weakness pressure, which dynamically up-weights the most difficult opponents to break through plateaus. We implement these mechanisms within FAMOU, a framework built upon the same foundation-model code-evolution paradigm as OpenEvolve and ShinkaEvolve. On the MCTF 2026 3v3 maritime capture-the-flag task, FAMOU consistently outperforms both baselines under two backbone LLMs, achieving the highest combined score (0.526) and the best generalization to unseen opponents (61.7% win rate), while ablations confirm that each mechanism contributes to performance. Notably, the LLM mutation process generates tactical structures entirely absent from the seed strategies -- including lookahead search and adaptive interception -- demonstrating that code-level evolution can produce nontrivial algorithmic innovations in adversarial settings. The FAMOU-evolved strategy further achieved 1st place in the hardware round-robin and 3rd in simulation at the AAMAS 2026 MCTF Competition, validating its real-world transferability. The optimized implementation and corresponding evaluation codes developed through our evolutionary process are available at: https://github.com/1xiangliu1/FAMOU-CoEvo
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。