recursive-arena
Combine recursive outer-loop refinement with multi-model arena generation each round. Use when users request recursive arena, multi-LLM consensus with iterative refinement, or recursive plus model-battle workflows.
来源信息
- 仓库
- lollipopkit/cc-plugins
- 最近来源活动
- 2026年3月14日 09:53
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 7
- 分支
- 0
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
文件资源管理器
2 个文件正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- recursive-arena
- description
- Combine recursive outer-loop refinement with multi-model arena generation each round. Use when users request recursive arena, multi-LLM consensus with iterative refinement, or recursive plus model-battle workflows.
- allowed-tools
- Read, Bash(python:*)
# Recursive-Arena
Use the orchestrator:
`python3 "${CLAUDE_PLUGIN_ROOT}/skills/recursive-arena/scripts/recursive_arena.py"`.
## How to run
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/skills/recursive-arena/scripts/recursive_arena.py" \
--prompt "<task>" --iters 4 --arena-iters 3 --json
```
Common flags: `--max-judges`, `--temperature`, `--max-tokens`, `--timeout`.
## Iteration Loop
For each outer iteration:
1. Run `multi-model` to generate a best candidate.
2. Use judge summaries as critique input.
3. Refine the prompt with the current best answer.
4. Keep the global best by score and continue.
## Configuration
Reuses `multi-model` `.env` configuration:
- `ARENA_MODELS`
- `ARENA_OPENAI_BASE_URL` or `ARENA_PROVIDER_<NAME>_BASE_URL`
- Optional API keys (`ARENA_OPENAI_API_KEY`, `ARENA_PROVIDER_<NAME>_API_KEY`)
Optional orchestration env:
- `RLM_ARENA_ARENA_ITERS` default inner arena iterations
- `RLM_ARENA_MAX_JUDGES` default judge cap
## Output and Safety
- Final answer is the best outer-iteration result.
- When useful, show a compact evolution table:
- `iteration`
- `winner_model_id` (numeric ID only)
- `avg_judge_score`
- `refinement_applied`
- Never disclose provider/model names.
- Never print secrets from `.env`.
在 GitHub 查看