Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
Autonomously improve a generated paper via external reviewer model review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
Autonomous research review loop using any OpenAI-compatible LLM API. Configure reviewer via MH Agent settings page or environment variables. Trigger with "auto review loop llm" or "llm review".
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax directly for external review. Trigger with "auto review loop minimax" or "minimax review".
Autonomous multi-round research review loop. Repeatedly reviews via external reviewer script, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants…
数学建模竞赛编程实现。根据建模报告编写代码、执行计算、收集结果。Use when user says "编程", "写代码", "code implementation".