reasoning-agent-workflows
Enables future agents to operate RLinf reasoning, agentic RL, coding online RL, rollout backend, SFT, reward, and service workflows.
- License 许可
- Apache-2.0
- 最近更新
- 2026-10-08
- Stars
- ★ 11
- Forks
- 3
01 前言 Front Matter
- name
- reasoning-agent-workflows
- license
- Apache 2.0
- metadata
- { "disco-role": "operating" }
- description
- Enables future agents to operate RLinf reasoning, agentic RL, coding online RL, rollout backend, SFT, reward, and service workflows.
- disable-model-invocation
- true
02 资源文件 4
- 参考文档references/reasoning-agent-recipes.md14.2 KB
- 参考文档references/rollout-backends-and-data.md12.6 KB
- 参考文档references/sft-offline-reward.md8.0 KB
- 参考文档references/troubleshooting.md12.0 KB
03 SKILL.md 正文
RLinf reasoning and agent workflow router
Use this sub-skill when a task involves RLinf text reasoning, VLM reasoning, agentic RL, coding online RL, SearchR1/rStar2/WideSeek-R1 style tool workflows, AgentLightning, rollout backends, SFT/VLM SFT, or reward/service integration.
Route first
- Install, Ray startup, node groups, generic placement syntax, and cluster health belong to the
setup-and-clustersub-skill. - Embodied simulator, robot, action-space, and VLA environment details belong to
embodied-workflows. - Metrics, checkpoints, standalone evaluation operations, profiling, CI selection, and runtime log triage belong to
operations-evaluation-debugging. - Registering a new model, environment, reward, algorithm, runner, worker, or tool parser belongs to
extension-development.
Operating loop
- Classify the workflow: math/VQA reasoning RL, PPO with critic, multi-turn agentic RL, coding online RL, AgentLightning, SFT/VLM SFT, or reward-model training.
- Inspect the user-supplied YAML with
scripts/inspect_agentic_config.pybefore launching any expensive run. - Verify prerequisites: model/tokenizer paths, dataset format, required service endpoints, judge/search/code-execution credentials, and rollout backend memory budget.
- Build or edit only the user’s target config/launcher. Use the bundled references below rather than asking future agents to open source examples or docs.
- Escalate to setup/operations/extension sub-skills for out-of-scope cluster, evaluation, or source-code-extension work.
Bundled references
references/reasoning-agent-recipes.md— recipe concepts for math/VQA GRPO/PPO, coding online RL, AgentLightning, SearchR1, rStar2, and WideSeek-R1.references/rollout-backends-and-data.md— SGLang/vLLM backend choices, actor/rollout/inference/reward data flow, dataset schemas, and service prerequisites.references/sft-offline-reward.md— SFT/VLM SFT, offline code validation, LoRA, reward-model training, and reward registry intersections.references/troubleshooting.md— reasoning/agentic-specific failure triage for sequence lengths, logprobs, services, backend OOMs, data loading, and AgentLightning.
Safe helper
scripts/inspect_agentic_config.pyreads one or more YAML files and reports task type, actor/rollout backends, length budget, algorithm settings, external services, and risky missing fields. It is static and non-mutating.
Evidence basis: distilled from RLinf v0.4.0 public configuration examples, English guides, runner/worker source, reasoning/VLM dataset loaders, reward registry, agent tool loops, rollout workers, and e2e configuration families.
04 同仓库更多 Skills
obsidian-clipper-template-creator
Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.
obsidian-clipper-template-creator
Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.
python-api
Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP/mAP semantics, and source-style import diagnostics.
file-evaluation
Folder-based PASCAL VOC AP/mAP evaluation from ground-truth and detection text files.
object-detection-metrics
Guides legacy Object-Detection-Metrics PASCAL VOC AP/mAP evaluation from detection text folders and direct Python API classes.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.