做智能体开发的团队终于有了更高效的搜索方案——Perplexity 的搜索集成让 MiniMax Agent 成本直降 27%，同时保持答案质量，做 RAG 或搜索增强型 Agent 的建议直接试试。
开源模型和智能体平台 MiniMax 宣布其 Agent 产品现已接入 Perplexity 的搜索基础设施。在超过 700 个智能体任务的基准测试中，Perplexity 在答案质量和片段密度上表现最佳，相比之前的默认搜索服务 Serper，每次任务工具调用次数从 32.6 次降至 17.8 次（减少 45%），Token 用量从 162.3M 降至 94.6M（减少 42%），通过率提升 2%，总成本降低 27%。这一改进对于依赖搜索循环的智能体工作流意义重大，更好的搜索片段意味着更少的搜索次数和更低的上下文开销。
MiniMax, a leading open source model and agent, is now powered by Perplexity’s search infrastructure
MiniMax, a leading open source model and agent, is now powered by Perplexity’s search infrastructure MiniMax_Agent @MiniMaxAgent MiniMax Agent now uses @perplexity_ai Search. We benchmarked 3 AI-native search providers across 700+ agent tasks. Perplexity delivered the best combination of answer quality and snippet density: more useful evidence per token, less irrelevant context, and lower end-to-end cost. Compared with Serper, our previous default: ⚡Tool calls per task: 17.8 vs 32.6 (45% reduction) 💰Token usage: 94.6M vs. 162.3M (42% reduction) 🔍Pass rate: +2% increase Total cost: 27% decrease in total cost savings In agent workflows, search is not a one-shot lookup. It is a loop. Better snippets mean better grounding. Better grounding means fewer searches, less context, better answers, and lower cost. One good search can save 14 bad ones. Now shipping in MiniMax Agent. agent.minimax.io HU 🔗 View Quoted Tweet 💬 9 🔄 0 ❤️ 59 👀 10028 📊 11 ⚡