Datasets: XiaomiMiMo / MiMo-V2.6-RL-oss Like 412 Follow Xiaomi MiMo 4.68k
Dataset Viewer
Auto-converted to Parquet API Embed Duplicate Data Studio
Subset (5)
code · 2.7k rows
Split (1)
train · 2.7k rows
SQL
Console
| data\_source stringclasses 1 value | ability stringclasses 1 value | agent\_name stringclasses 1 value | prompt listlengths 1 1 | reward\_model dict | extra\_info dict | | ---------------------------------- | ----------------------------- | --------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "\[FEAT\] Make \`secrets\` parameter optional so we can use this action just to get the token.\\n\\*Is your feature request related to a problem? Please describe.\\*\\r\\nThe \`secrets\` parameter should not be mandatory. There is the option for \`exportToken\`, which is what I want to use to configure the Vaul... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 1, "instance\_id": "format-code-task-001457", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-001457:latest\\", \\"instance\_id\\": \\"format-code-task-001457\\", \\"problem\_statement\\": \\"\[FEAT\] Make \`se... | | opensource-code | swe | mimo\_swe\_agent | \ { "content": "I want \`gz::sim::SdfEntityCreator\` to support creating ECS entities from SDF projectors. Given an existing \`SdfEntityCreator\`, calling \`Entity CreateEntities(const sdf::Projector \*)\` with a projector named \`projector\`, a raw pose of \`(1, 2, 3, 0, 0, 0)\`, near clip \`2.0\`, far clip \`7.0\`, horizontal... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 2, "instance\_id": "format-code-task-001240", "instance\_json": "{\\"cwd\\": \\"/workspace/repo\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-001240:latest\\", \\"instance\_id\\": \\"format-code-task-001240\\", \\"problem\_statement\\": \\"I want \`... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "## Role REST API silently drops \`handle\` on create / update\\n\\nI'm wiring up a small admin tool against the Corteza system API and I want to give each role a stable, machine-friendly \`handle\` next to its display \`name\` (similar to what users and the signup endpoint already accept). The \`Role\` type... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 3, "instance\_id": "format-code-task-000723", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-000723:latest\\", \\"instance\_id\\": \\"format-code-task-000723\\", \\"problem\_statement\\": \\"## Role REST AP... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "# Problem Statement\\n\\n我现在在 Cortex 里上传 Alertmanager 配置时，receiver 的 HTTP 通知鉴权基本只能用 basic auth 或 bearer token，但我们这边的 webhook 接口要求走 OAuth2 client credentials。能不能让 \`http\_config\` 这类通知配置直接支持 \`oauth2\`，比如用 client id、inline secret 和 token URL 去拿 token？另外这个配置是租户自己传的，最好不要允许它通过 \`client\_secret\_file\` 去读服务器上的本地文... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 4, "instance\_id": "format-code-task-000718", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-000718:latest\\", \\"instance\_id\\": \\"format-code-task-000718\\", \\"problem\_statement\\": \\"# Problem State... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "## PI and LogEI acquisition functions crash when called\\n\\nI'm using RoBO for some Bayesian optimization experiments. The default \`EI\`\\nacquisition function works fine, so I wanted to compare against \`PI\` and\\n\`LogEI\` on the same problem.\\n\\nI set them up the same way I set up \`EI\` (same model, sa... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 6, "instance\_id": "format-code-task-000484", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-000484:latest\\", \\"instance\_id\\": \\"format-code-task-000484\\", \\"problem\_statement\\": \\"## PI and LogEI... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "## BroydenSolver behaves inconsistently with other nonlinear solvers (label + recording)\\n\\nI'm running a model where I'm experimenting with different nonlinear solvers\\n(BroydenSolver vs NewtonSolver vs NonlinearBlockGS) on the same group, and\\nI have a case recorder attached so I can compare the... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 7, "instance\_id": "format-code-task-000189", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-000189:latest\\", \\"instance\_id\\": \\"format-code-task-000189\\", \\"problem\_statement\\": \\"## BroydenSolve... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "## S3 bucket client keeps retrying after the request context is canceled\\n\\nWhen running Cortex against S3-backed object storage, I noticed that if an in-flight operation's context gets canceled (either explicitly, or because an upstream deadline expires), the bucket client doesn't actually stop r... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 8, "instance\_id": "format-code-task-000720", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-000720:latest\\", \\"instance\_id\\": \\"format-code-task-000720\\", \\"problem\_statement\\": \\"## S3 bucket cl... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "I want the friendship model API to treat a stored friendship row as a bidirectional relationship between two Django users. The library should expose \`Friendship.objects.friends\_for\_user(user)\`, returning a list of dictionaries where each item has \`friend\` set to the other \`User\` and \`friendship\` s... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 9, "instance\_id": "format-code-task-001661", "instance\_json": "{\\"cwd\\": \\"/workspace/repo\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-001661:latest\\", \\"instance\_id\\": \\"format-code-task-001661\\", \\"problem\_statement\\": \\"I want t... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "Dyson integration does not expose humidity or air quality (pm25) to homekit\\n<!-- READ THIS FIRST:\\r\\n - If you need additional help with this template, please refer to https://www.home-assistant.io/help/reporting\_issues/\\r\\n - Make sure you are running the latest version of Home Assistant befor... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 10, "instance\_id": "format-code-task-001499", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-001499:latest\\", \\"instance\_id\\": \\"format-code-task-001499\\", \\"problem\_statement\\": \\"Dyson integrat... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "## Custom \`dgs.graphql.graphiql.path\` doesn't actually work end-to-end\\n\\nI'm using the WebFlux variant of dgs-framework and I wanted to expose GraphiQL on a non-default path (we have a routing convention internally), so in my \`application.yml\` I set:\\n\\n\`\`\`yaml\\ndgs:\\n graphql:\\n graphiql:\\n ... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 11, "instance\_id": "format-code-task-000173", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-000173:latest\\", \\"instance\_id\\": \\"format-code-task-000173\\", \\"problem\_statement\\": \\"## Custom \`dgs... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "pvsystem.Array.get\_irradiance raises an error if solar\_zenith is passed as a float\\n\\*Bug Description\\*\\r\\n\`pvsystem.get\_irradiance\` documentation says solar\_zenith can be passed as a float or a Series. However, if \`dni\_extra\` is not defined and \`solar\_zenith\` is passed as float, then \`solar\_zenit... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 12, "instance\_id": "format-code-task-002366", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-002366:latest\\", \\"instance\_id\\": \\"format-code-task-002366\\", \\"problem\_statement\\": \\"pvsystem.Array... | | opensource-code | swe | mimo\swe\_agent | \[ { "content": "ufuzz failure\\n\`\`\`js\\r\\n// original code\\r\\n// (beautified)\\r\\nvar \_calls\ = 10, a = 100, b = 10, c = 0;\\r\\n\\r\\nfunction f0(arguments\1, a\_1) {\\r\\n {\\r\\n var brake1 = 5;\\r\\n L12709: while ((c = c + 1) + a++ && --brake1 > 0) {\\r\\n try {\\r\\n } catch (undefined\... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 13, "instance\_id": "format-code-task-001933", "instance\_json": "{\\"cwd\\": \\"/testbed\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-001933:latest\\", \\"instance\_id\\": \\"format-code-task-001933\\", \\"problem\_statement\\": \\"ufuzz failure\\... | | opensource-code | swe | mimo\_swe\_agent | \[ { "content": "I want the ReNative CLI to provide hook-management commands for project build hooks: \`rnv hooks run\`, \`rnv hooks list\`, and \`rnv hooks pipes\`.\\n\\n\`rnv hooks run -x <hookName>\` and \`rnv hooks run --exe-method <hookName>\` should configure the project when a project config exists, load the project bu... | { "ground\_truth": "", "style": "rule" } | { "dataset\_type": "opensource-code", "index": 14, "instance\_id": "format-code-task-001190", "instance\_json": "{\\"cwd\\": \\"/workspace/repo\\", \\"dataset\_type\\": \\"opensource-code\\", \\"docker\_image\\": \\"format-code-task-001190:latest\\", \\"instance\_id\\": \\"format-code-task-001190\\", \\"problem\_statement\\": \\"I want ... |
End of preview. [Expand in Data Studio
---
Agentic RL Environments
RL training environments for LLM agents.
| Domain | Task Family | Verifier | | ------- | -------------------------- | -------------------- | | Code | Software engineering | Executable tests | | Cyber | Vulnerability reproduction | Rule checks | | General | Knowledge work | Rubric-based judging | | Visual | Web development | Visual grading | | Music | Symbolic music composition | Rule checks |
- Docker images: <https://hub.docker.com/r/xiaomimimo/mimo-v2.6-rl-oss>
- Training code: <https://github.com/XiaomiMiMo/verl>
Copy to bucket new
Use this dataset
Downloads last month 8,294
Number of rows:
7,780
Total file size:
12.1 GB
Models trained or fine-tuned on XiaomiMiMo/MiMo-V2.6-RL-oss
Reinforcement Learning • 8B • Updated about 5 hours ago
Reinforcement Learning • 8B • Updated 4 minutes ago