SwarmEvolve：用潜在空间智能体群加速演化搜索
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
几百个小智能体在潜在空间里群聊协作，几分钟跑出别人一小时的搜索结果，还用 Qwen3 8B 改进了 AlphaEvolve 的解，省钱又快。
SwarmEvolve 是一个 LLM 引导的演化搜索框架，每轮调度数百个低成本智能体，在潜在空间中推理而不解码成文本，并通过传递 KV 缓存共享信息。框架用隐藏状态向量距离做新颖性过滤，由 summarizer 智能体汇总所有成员的 KV 缓存实现思想交叉。在 21 个数学发现与科学计算问题上，SwarmEvolve 取得最高平均分，中位数 3 到 8 分钟即可达到其他框架 60 分钟的最好成绩。在部分问题上，使用 Qwen3 8B 的 SwarmEvolve 改进了 AlphaEvolve 用前沿 LLM 首先找到的解。
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches. Each swarm studies the problem from a different angle. A novelty filter keeps the most distinct agent ideas by directly measuring the distances between the agents' hidden state vectors. Crossover of ideas happens naturally in latent space, as a summarizer agent receives the combined KV caches of all swarm members. On 21 problems in mathematical discovery and scientific computing, SwarmEvolve gets the highest average score and needs a median of only 3 to 8 minutes to reach the best scores that other state-of-the-art frameworks reach in 60 minutes. On several problems, SwarmEvolve with Qwen3 8B improves on the solutions that AlphaEvolve first found with frontier LLMs. Our work shows that agent swarms that communicate in latent space offer a fast, low-cost approach to program search for scientific problems.