{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "kimi-team-partial-rollout-long2short-2025",
    "title": "Kimi Team: partial-rollout long-context RL and long-to-short transfer",
    "summary": "Integrated long-context reasoning RL with reusable partial rollouts, policy optimization and multimodal data, and transferred longer reasoning behavior toward shorter-response models through length control and merging.",
    "boundary": "RL, online mirror descent and distillation/merging have predecessors. Report includes long-CoT warmup SFT, so not a no-supervision recipe. Context scaling is observed on specified experiments, not an unlimited scaling law; inference traces are not proof of faithful internal search.",
    "area": "Multimodal reasoning-training systems",
    "topic": "Artificial intelligence",
    "year": 2025,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "kimi-team-partial-rollout-long2short-2025",
    "target": {
      "record_id": "urn:uuid:155f3789-6be0-47c2-a5e3-a22c6f47ecbd",
      "version": 1,
      "content_hash": "sha256:55c2d9a6c8870a420423c601b05c1fa4c0b4fb5cd9b367ae6fd05a83575afd9c"
    },
    "humans": [],
    "authors_complete": false,
    "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "cur20261015-arxiv-2501-12599v1",
        "title": "Kimi k1.5: Scaling Reinforcement Learning with LLMs",
        "url": "https://arxiv.org/abs/2501.12599v1"
      },
      {
        "id": "cur20261015-support-kimi-team-partial-rollout-long2short-2025",
        "title": "Kimi Team: partial-rollout long-context RL and long-to-short transfer — author/institutional project",
        "url": "https://github.com/MoonshotAI/Kimi-k1.5"
      }
    ],
    "points": "70000",
    "published_grade": {
      "id": "kimi-team-partial-rollout-long2short-2025",
      "entry_id": "kimi-team-partial-rollout-long2short-2025",
      "band": "B",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:155f3789-6be0-47c2-a5e3-a22c6f47ecbd",
        "version": 1,
        "content_hash": "sha256:55c2d9a6c8870a420423c601b05c1fa4c0b4fb5cd9b367ae6fd05a83575afd9c"
      },
      "what_changed": "Integrated long-context reasoning RL with reusable partial rollouts, policy optimization and multimodal data, and transferred longer reasoning behavior toward shorter-response models through length control and merging.",
      "scope": "Integrated long-context reasoning RL with reusable partial rollouts, policy optimization and multimodal data, and transferred longer reasoning behavior toward shorter-response models through length control and merging. RL, online mirror descent and distillation/merging have predecessors. Report includes long-CoT warmup SFT, so not a no-supervision recipe. Context scaling is observed on specified experiments, not an unlimited scaling law; inference traces are not proof of faithful internal search.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:155f3789-6be0-47c2-a5e3-a22c6f47ecbd",
        "version": 1,
        "content_hash": "sha256:55c2d9a6c8870a420423c601b05c1fa4c0b4fb5cd9b367ae6fd05a83575afd9c"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-10-16T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "organization",
          "name": "Kimi Team",
          "note": "Cited historical collaboration, not a platform organization account; individual attribution remains incomplete.",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Kimi k1.5: Scaling Reinforcement Learning with LLMs",
            "url": "https://arxiv.org/abs/2501.12599v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Kimi k1.5: Scaling Reinforcement Learning with LLMs",
            "url": "https://arxiv.org/abs/2501.12599v1"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Kimi Team: partial-rollout long-context RL and long-to-short transfer — author/institutional project",
            "url": "https://github.com/MoonshotAI/Kimi-k1.5"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "RL, online mirror descent and distillation/merging have predecessors. Report includes long-CoT warmup SFT, so not a no-supervision recipe. Context scaling is observed on specified experiments, not an unlimited scaling law; inference traces are not proof of faithful internal search.",
        "domain": "Multimodal reasoning-training systems"
      },
      "sources": [
        {
          "citation": "Kimi k1.5: Scaling Reinforcement Learning with LLMs",
          "url": "https://arxiv.org/abs/2501.12599v1"
        },
        {
          "citation": "Kimi Team: partial-rollout long-context RL and long-to-short transfer — author/institutional project",
          "url": "https://github.com/MoonshotAI/Kimi-k1.5"
        }
      ],
      "statement": "# Kimi Team: partial-rollout long-context RL and long-to-short transfer\n\nIntegrated long-context reasoning RL with reusable partial rollouts, policy optimization and multimodal data, and transferred longer reasoning behavior toward shorter-response models through length control and merging.\n\n## Scientific scope\n\nRL, online mirror descent and distillation/merging have predecessors. Report includes long-CoT warmup SFT, so not a no-supervision recipe. Context scaling is observed on specified experiments, not an unlimited scaling law; inference traces are not proof of faithful internal search.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\n\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://arxiv.org/abs/2501.12599v1)\n- [Kimi Team: partial-rollout long-context RL and long-to-short transfer — author/institutional project](https://github.com/MoonshotAI/Kimi-k1.5)\n",
      "summary": "Integrated long-context reasoning RL with reusable partial rollouts, policy optimization and multimodal data, and transferred longer reasoning behavior toward shorter-response models through length control and merging.",
      "title": "Kimi Team: partial-rollout long-context RL and long-to-short transfer"
    },
    "record_id": "urn:uuid:155f3789-6be0-47c2-a5e3-a22c6f47ecbd",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:155f3789-6be0-47c2-a5e3-a22c6f47ecbd",
      "version": 1,
      "content_hash": "sha256:55c2d9a6c8870a420423c601b05c1fa4c0b4fb5cd9b367ae6fd05a83575afd9c"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:41c33c43e35dfc38d8ddbb0442c263b6a8df60a298f2e7dfbb28c8f4ede9ee49"
  },
  "target": {
    "record_id": "urn:uuid:155f3789-6be0-47c2-a5e3-a22c6f47ecbd",
    "version": 1,
    "content_hash": "sha256:55c2d9a6c8870a420423c601b05c1fa4c0b4fb5cd9b367ae6fd05a83575afd9c"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "kimi-team-partial-rollout-long2short-2025",
    "entry_id": "kimi-team-partial-rollout-long2short-2025",
    "revision": 1,
    "title": "Kimi Team: partial-rollout long-context RL and long-to-short transfer",
    "context": "Multimodal reasoning-training systems",
    "track": "Human-designed research method or resource",
    "band": "B",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Integrated long-context reasoning RL with reusable partial rollouts, policy optimization and multimodal data, and transferred longer reasoning behavior toward shorter-response models through length control and merging.",
    "scope": "Integrated long-context reasoning RL with reusable partial rollouts, policy optimization and multimodal data, and transferred longer reasoning behavior toward shorter-response models through length control and merging. RL, online mirror descent and distillation/merging have predecessors. Report includes long-CoT warmup SFT, so not a no-supervision recipe. Context scaling is observed on specified experiments, not an unlimited scaling law; inference traces are not proof of faithful internal search.",
    "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. RL, online mirror descent and distillation/merging have predecessors. Report includes long-CoT warmup SFT, so not a no-supervision recipe. Context scaling is observed on specified experiments, not an unlimited scaling law; inference traces are not proof of faithful internal search.",
    "references": [
      {
        "title": "Kimi k1.5: Scaling Reinforcement Learning with LLMs",
        "url": "https://arxiv.org/abs/2501.12599v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      },
      {
        "title": "Kimi Team: partial-rollout long-context RL and long-to-short transfer — author/institutional project",
        "url": "https://github.com/MoonshotAI/Kimi-k1.5",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      }
    ],
    "roles": [
      {
        "who": "Source-listed authors and technical contributors",
        "credit": "SCIENCE",
        "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities."
      }
    ],
    "target": {
      "record_id": "urn:uuid:155f3789-6be0-47c2-a5e3-a22c6f47ecbd",
      "version": 1,
      "content_hash": "sha256:55c2d9a6c8870a420423c601b05c1fa4c0b4fb5cd9b367ae6fd05a83575afd9c"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "70000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}