Benchmark for evaluating advanced reasoning, recursive dependency resolution, and robustness capabilities of large language models in dynamic, noisy, and structurally challenging environments.
-
Updated
May 15, 2026 - Python
Benchmark for evaluating advanced reasoning, recursive dependency resolution, and robustness capabilities of large language models in dynamic, noisy, and structurally challenging environments.
跨多模态动漫资产自动化处理与本地化 Agent 矩阵
Multi-agent code review CLI with long-chain reasoning. Five specialist agents (security, performance, style, architecture, test) review in parallel; a coordinator synthesizes findings into one prioritized action list. Works with any OpenAI-compatible endpoint.
职途先知 (Career Prophet) — 基于小米大模型的多智能体协作式大学生职业规划AI Agent。4阶段流水线+6跳长链推理,3所高校内测,覆盖2000+学生,日均处理300万tokens。
企业级 DevOps 与云原生架构自动排障多 Agent 平台
Autonomous multi-agent codebase modernization & tech debt hunter — 7 specialized agents, 4-pass long-chain reasoning, powered by Xiaomi MiMo V2.5
Multi-agent long-chain reasoning research system. Plan → Search → Verify → Synthesize → Write. Powered by Xiaomi MiMo.
Add a description, image, and links to the long-chain-reasoning topic page so that developers can more easily learn about it.
To associate your repository with the long-chain-reasoning topic, visit your repo's landing page and select "manage topics."