如果你做过生命科学数据分析、系统生物学建模、知识图谱、多组学整合，看到“医学世界模型”这个概念，第一反应可能是：

这不就是 systems biology 吗？

生命科学不是早就在建模基因网络、代谢通路、信号通路、疾病机制了吗？

这个问题非常合理。

如果所谓医学世界模型只是把系统生物学、数字孪生、AI 大模型重新包装一下，那它确实没有太多工程价值。

但从系统设计角度看，二者的核心差别不是“名字不同”，而是对象边界不同。

系统生物学模型通常重点表达：

component -> relation -> pathway -> network -> mechanism

医学世界模型则需要进一步表达：

state + action + evidence -> transition hypothesis -> feedback update

换句话说：

  • 系统生物学主要帮助我们理解生命系统如何运行；
  • 医学世界模型进一步要支持“如果采取某个动作，个体状态可能如何变化”的干预推演；
  • 可驾驭医学世界模型还要把目标、边界、证据链、人类复核和反馈校准纳入系统架构。

这篇文章不讨论宏大概念，而是用开发者视角拆开这个问题。

1. 三类模型的工程边界

先用一张表区分预测模型、系统生物学模型和医学世界模型。

模型类型 核心问题 主要对象 典型输出 工程关键词
预测模型 未来风险有多高？ features, labels risk score, class, probability classification / regression
系统生物学模型 生命系统如何运行？ genes, proteins, pathways, networks mechanism, network dynamics graph / ODE / network model
医学世界模型 采取某个动作后，状态可能如何变化？ state, action, transition, evidence, feedback transition hypothesis, audit trail state-action-feedback loop

一个普通风险预测模型可以写成：

risk = predict_risk(patient_features)

一个系统生物学模型可能更像：

network_state = simulate_pathway_dynamics(
    pathway_graph,
    initial_conditions,
    perturbation
)

而医学世界模型更接近：

transition = estimate_transition_hypothesis(
    state=current_patient_state,
    action=candidate_intervention,
    evidence=evidence_chain
)

feedback = collect_feedback(
    patient_id=patient_id,
    action=candidate_intervention,
    time_window_weeks=8
)

updated_state = update_state(
    previous_state=current_patient_state,
    action=candidate_intervention,
    transition=transition,
    feedback=feedback
)

这里的关键不是模型形式更复杂，而是系统对象发生了变化：

从 feature prediction
到 mechanism modeling
再到 action-conditioned transition reasoning

2. 系统生物学不是没有 action，但 action 通常不是决策对象

需要先说明：系统生物学并不是不研究扰动和干预。

系统生物学当然可以处理：

  • gene knockout；
  • drug perturbation；
  • pathway activation / inhibition；
  • environment change；
  • ODE simulation；
  • network control；
  • multi-omics perturbation response。

所以不能简单说：

systems biology has no action
medical world model has action

这个说法不严谨。

更准确的说法是：

系统生物学可以研究扰动和响应，但医学世界模型需要把 action 作为面向个体决策的结构化对象，并把它放入 evidence、transition、feedback 和 audit loop 中。

在系统生物学中，perturbation 可能是模型输入之一：

result = simulate_network(
    graph=pathway_graph,
    perturbation={"gene_x": "knockout"}
)

但在医学世界模型中，action 不只是一个扰动参数，而是一个可执行、可记录、可审计、可反馈的对象。

例如：

from dataclasses import dataclass
from typing import List, Dict

@dataclass
class InterventionAction:
    action_id: str
    category: str
    description: str
    target_mechanisms: List[str]
    intensity: str
    duration_weeks: int
    monitoring_markers: List[str]
    safety_constraints: List[str]

示例：

action = InterventionAction(
    action_id="nutrition_low_glycemic_8w",
    category="nutrition",
    description="8-week low-glycemic dietary adjustment",
    target_mechanisms=[
        "postprandial_glucose_variability",
        "insulin_resistance",
        "weight_management"
    ],
    intensity="moderate",
    duration_weeks=8,
    monitoring_markers=[
        "fasting_glucose",
        "hba1c",
        "weight",
        "waist_circumference"
    ],
    safety_constraints=[
        "not a treatment prescription",
        "clinical review required if medication is involved",
        "stop or refer if red flags appear"
    ]
)

这就是工程结构上的区别：

perturbation parameter != intervention action object

3. 系统生物学模型更像 mechanism graph

一个简化的系统生物学模型可以用图表示。

@dataclass
class BiologicalNode:
    node_id: str
    node_type: str  # gene, protein, metabolite, pathway, phenotype
    name: str

@dataclass
class BiologicalEdge:
    source: str
    target: str
    relation: str  # activates, inhibits, regulates, correlates_with
    evidence_strength: str

@dataclass
class MechanismGraph:
    nodes: List[BiologicalNode]
    edges: List[BiologicalEdge]

例如：

mechanism_graph = MechanismGraph(
    nodes=[
        BiologicalNode("n1", "pathway", "insulin_signaling"),
        BiologicalNode("n2", "phenotype", "glucose_variability"),
        BiologicalNode("n3", "phenotype", "fatigue")
    ],
    edges=[
        BiologicalEdge(
            source="n1",
            target="n2",
            relation="regulates",
            evidence_strength="moderate"
        ),
        BiologicalEdge(
            source="n2",
            target="n3",
            relation="associated_with",
            evidence_strength="low"
        )
    ]
)

这个结构非常有价值，因为它帮助我们表达：

  • 哪些机制可能相关；
  • 哪些通路可能被扰动；
  • 哪些节点之间存在调控关系；
  • 哪些 phenotype 可能由多个机制共同影响。

但它还不是完整医学世界模型。

因为它还没有明确回答：

当前个体状态是什么？
准备采取什么动作？
动作后预期状态如何变化？
证据链是什么？
反馈窗口是什么？
如果反馈不符合预期，如何更新？

4. 医学世界模型需要 State 对象

医学世界模型首先需要定义个体状态。

from dataclasses import dataclass
from typing import Optional

@dataclass
class PatientState:
    patient_id: str
    demographics: Dict
    clinical_markers: Dict
    lifestyle: Dict
    symptoms: List[str]
    medications: List[str]
    omics: Optional[Dict] = None
    wearable: Optional[Dict] = None
    mechanism_context: Optional[Dict] = None

示例：

state = PatientState(
    patient_id="P001",
    demographics={
        "age": 52,
        "sex": "unspecified"
    },
    clinical_markers={
        "bmi": 29.1,
        "fasting_glucose": 6.2,
        "hba1c": 6.0,
        "triglycerides": 2.1,
        "hdl_c": 0.95
    },
    lifestyle={
        "sleep_hours": 5.8,
        "exercise_frequency_per_week": 1,
        "diet_pattern": "high_refined_carbohydrate"
    },
    symptoms=[
        "fatigue",
        "post_meal_sleepiness"
    ],
    medications=[],
    mechanism_context={
        "possible_insulin_resistance": True,
        "possible_glucose_variability": True,
        "data_quality": "partial"
    }
)

这里有一个重要原则：

state 不是越大越好，而是要能被 action、transition 和 feedback 引用。

如果一个字段不能影响动作选择，也不能用于反馈更新，那它可能只是数据堆积，不是有效状态表示。

5. Transition 不是疗效预测，而是状态转移假设

开发者很容易写出这样的函数：

next_state = predict_next_state(state, action)

但在医学场景中，这个命名风险很高。

它像是在说模型可以预测个体疗效。对于当前大多数医学 AI 系统来说，这样的表述过强。

更稳妥的写法是：

transition = estimate_transition_hypothesis(
    state=state,
    action=action,
    evidence=evidence_chain
)

也就是：状态转移假设。

@dataclass
class TransitionHypothesis:
    expected_direction: Dict
    mechanism_rationale: List[str]
    uncertainty_level: str
    time_window_weeks: int
    assumptions: List[str]
    limitations: List[str]

示例：

transition = TransitionHypothesis(
    expected_direction={
        "fasting_glucose": "decrease_possible",
        "postprandial_glucose": "decrease_possible",
        "weight": "slight_decrease_possible",
        "energy_level": "may_improve"
    },
    mechanism_rationale=[
        "lower refined carbohydrate intake may reduce postprandial glucose excursions",
        "weight reduction may improve insulin sensitivity",
        "improved sleep may reduce metabolic stress"
    ],
    uncertainty_level="moderate",
    time_window_weeks=8,
    assumptions=[
        "adequate adherence",
        "no major medication change",
        "baseline data quality is acceptable"
    ],
    limitations=[
        "individual response may vary",
        "not a treatment effect prediction",
        "not a substitute for clinical judgment"
    ]
)

注意这里用的是：

decrease_possible
may_improve
hypothesis
uncertainty
limitations

而不是：

will decrease
will reverse
will cure

这是医学 AI 工程实现里非常关键的安全边界。

6. EvidenceChain：不要让模型只生成建议

如果一个系统只输出：

recommendation = "reduce refined carbohydrates and increase exercise"

这还不是医学世界模型。

医学世界模型必须能说明：

  • 为什么提出这个 action；
  • 机制依据是什么；
  • 证据强度如何；
  • 适用边界是什么；
  • 不确定性在哪里。

可以定义 evidence chain：

@dataclass
class EvidenceItem:
    source_type: str  # guideline, trial, mechanism, omics, individual_context
    description: str
    strength: str
    reference: str | None = None

@dataclass
class EvidenceChain:
    items: List[EvidenceItem]
    overall_strength: str
    uncertainty: str
    limitations: List[str]

示例：

evidence_chain = EvidenceChain(
    items=[
        EvidenceItem(
            source_type="mechanism",
            description="Reduced refined carbohydrate intake may reduce postprandial glucose excursions.",
            strength="moderate"
        ),
        EvidenceItem(
            source_type="individual_context",
            description="Current state includes high refined carbohydrate pattern and low exercise frequency.",
            strength="contextual"
        ),
        EvidenceItem(
            source_type="clinical_guideline",
            description="Lifestyle intervention is commonly recommended for metabolic risk management.",
            strength="high"
        )
    ],
    overall_strength="moderate",
    uncertainty="moderate",
    limitations=[
        "adherence is uncertain",
        "individual response may vary",
        "clinical review required when disease or medication is involved"
    ]
)

工程原则：

recommendation without evidence object = weak output
action + transition + evidence + feedback plan = stronger world-model output

7. Feedback：世界模型必须能更新

医学世界模型不能只是一次性输出。

它必须支持 feedback update。

@dataclass
class FollowUpFeedback:
    patient_id: str
    action_id: str
    timepoint_weeks: int
    observed_markers: Dict
    adherence: Dict
    symptom_changes: Dict
    adverse_events: List[str]

示例：

feedback = FollowUpFeedback(
    patient_id="P001",
    action_id="nutrition_low_glycemic_8w",
    timepoint_weeks=8,
    observed_markers={
        "fasting_glucose": 5.8,
        "hba1c": 5.8,
        "weight_change_kg": -2.1,
        "waist_change_cm": -3.0
    },
    adherence={
        "nutrition": "medium",
        "exercise": "low",
        "sleep": "unchanged"
    },
    symptom_changes={
        "fatigue": "slightly_improved",
        "post_meal_sleepiness": "improved"
    },
    adverse_events=[]
)

然后把反馈写入更新逻辑：

def update_world_model_state(
    previous_state: PatientState,
    action: InterventionAction,
    transition: TransitionHypothesis,
    feedback: FollowUpFeedback
):
    update_record = {
        "previous_state": previous_state,
        "action": action,
        "expected_transition": transition,
        "observed_feedback": feedback,
        "interpretation": None,
        "next_step": None
    }

    if feedback.adherence.get("nutrition") == "medium":
        update_record["interpretation"] = (
            "Partial improvement observed; adherence may limit effect size."
        )
        update_record["next_step"] = (
            "Review adherence barriers and consider adjusting action intensity."
        )
    else:
        update_record["interpretation"] = (
            "Observed feedback should be interpreted with caution."
        )
        update_record["next_step"] = (
            "Collect more context before updating the transition hypothesis."
        )

    return update_record

如果没有 feedback update，这个系统更像推荐系统，不像世界模型。

8. 因果边界：action-conditioned reasoning 不能只靠相关性

医学世界模型一旦要回答：

if action A, then what may happen?

就进入了因果问题。

所以 transition 不应该只是相关性预测：

transition = correlate(state_features, future_outcomes)

而应该显式记录因果假设和不确定性：

@dataclass
class CausalAssumption:
    assumption_id: str
    description: str
    possible_confounders: List[str]
    applicable_population: str
    evidence_level: str
    uncertainty: str

示例：

causal_assumption = CausalAssumption(
    assumption_id="CA001",
    description=(
        "Reducing refined carbohydrate intake may reduce postprandial glucose "
        "excursions in individuals with diet-related glucose variability."
    ),
    possible_confounders=[
        "medication_change",
        "physical_activity_change",
        "sleep_change",
        "stress_change",
        "baseline_disease_status"
    ],
    applicable_population="health-management context with mild metabolic risk",
    evidence_level="moderate",
    uncertainty="individual_response_varies"
)

这不是说每个系统都必须完整实现因果推断引擎，而是说：

只要系统输出 action-conditioned transition，就必须显式记录因果假设、适用边界和不确定性。

否则 transition hypothesis 很容易退化成相关性外推。

9. SafetyGate：医学系统必须先过安全边界

医学世界模型不能只追求“更聪明”。

它必须先有安全边界。

@dataclass
class SafetyGateResult:
    passed: bool
    red_flags: List[str]
    contraindications: List[str]
    required_review: List[str]
    notes: List[str]

示例：

def run_safety_gate(
    state: PatientState,
    action: InterventionAction
) -> SafetyGateResult:
    red_flags = []
    contraindications = []
    required_review = []

    if state.clinical_markers.get("fasting_glucose", 0) > 13.9:
        red_flags.append("very_high_glucose_requires_clinical_evaluation")

    if "chest_pain" in state.symptoms:
        red_flags.append("chest_pain_requires_urgent_evaluation")

    if state.medications:
        required_review.append("medication_context_requires_clinician_review")

    passed = len(red_flags) == 0 and len(contraindications) == 0

    return SafetyGateResult(
        passed=passed,
        red_flags=red_flags,
        contraindications=contraindications,
        required_review=required_review,
        notes=[
            "not medical advice",
            "not a validated treatment planning system",
            "human review required in clinical context"
        ]
    )

原则：

No safety gate, no medical world-model deployment.

10. AuditLog：为什么每一步都要留痕

医学世界模型必须能回答：

  • 当时的 state 是什么？
  • 为什么选择这个 action？
  • transition hypothesis 是什么？
  • evidence chain 来自哪里？
  • 谁复核过？
  • feedback 和预期是否一致？
  • 如果不一致，下一轮怎么更新？

可以定义 audit log：

@dataclass
class AuditLog:
    record_id: str
    patient_id: str
    state_snapshot_id: str
    action_id: str
    transition_id: str
    evidence_chain_id: str
    safety_gate_id: str
    reviewer: str
    decision: str
    timestamp: str

示例：

audit_log = AuditLog(
    record_id="AUDIT_20260521_001",
    patient_id="P001",
    state_snapshot_id="STATE_20260521",
    action_id="nutrition_low_glycemic_8w",
    transition_id="TRANSITION_20260521_001",
    evidence_chain_id="EVIDENCE_20260521_001",
    safety_gate_id="SAFETY_20260521_001",
    reviewer="human_expert",
    decision="approved_for_health_management_context",
    timestamp="2026-05-21T20:00:00+08:00"
)

医学世界模型不是“生成一句更好的答案”，而是让一次推演过程可追踪、可审计、可反馈。

11. 一个最小医学世界模型工作流

把上面的对象组合起来，可以得到一个最小工作流：

def medical_world_model_loop(patient_id: str):
    # 1. Observe current state
    state = observe_patient_state(patient_id)

    # 2. Retrieve mechanism context
    mechanism_context = retrieve_mechanism_context(state)

    # 3. Generate candidate actions
    candidate_actions = generate_candidate_actions(
        state=state,
        mechanism_context=mechanism_context
    )

    transition_candidates = []

    for action in candidate_actions:
        # 4. Safety gate first
        safety = run_safety_gate(state, action)

        if not safety.passed:
            continue

        # 5. Build evidence chain
        evidence = build_evidence_chain(
            state=state,
            action=action,
            mechanism_context=mechanism_context
        )

        # 6. Estimate transition hypothesis
        transition = estimate_transition_hypothesis(
            state=state,
            action=action,
            evidence=evidence
        )

        transition_candidates.append({
            "action": action,
            "transition": transition,
            "evidence": evidence,
            "safety": safety
        })

    # 7. Human-in-the-loop review
    selected = human_expert_review(transition_candidates)

    # 8. Collect follow-up feedback
    feedback = collect_follow_up_feedback(
        patient_id=patient_id,
        action_id=selected["action"].action_id,
        time_window_weeks=selected["transition"].time_window_weeks
    )

    # 9. Update model state
    updated_record = update_world_model_state(
        previous_state=state,
        action=selected["action"],
        transition=selected["transition"],
        feedback=feedback
    )

    # 10. Write audit log
    audit_log = write_audit_log(
        state=state,
        selected=selected,
        feedback=feedback,
        updated_record=updated_record
    )

    return {
        "updated_record": updated_record,
        "audit_log": audit_log
    }

这个 workflow 的关键不是代码本身，而是对象顺序：

state
  -> mechanism context
  -> candidate action
  -> safety gate
  -> evidence chain
  -> transition hypothesis
  -> human review
  -> feedback
  -> update
  -> audit log

这就是医学世界模型和普通系统生物学图谱之间的工程差异。

12. JSON 示例：一次 transition record

下面是一个简化 JSON，表示一次医学世界模型推演记录：

{
  "state": {
    "patient_id": "P001",
    "state_snapshot_id": "STATE_20260521",
    "clinical_markers": {
      "bmi": 29.1,
      "fasting_glucose": 6.2,
      "hba1c": 6.0,
      "triglycerides": 2.1
    },
    "lifestyle": {
      "sleep_hours": 5.8,
      "exercise_frequency_per_week": 1,
      "diet_pattern": "high_refined_carbohydrate"
    },
    "mechanism_context": {
      "possible_insulin_resistance": true,
      "possible_glucose_variability": true,
      "data_quality": "partial"
    }
  },
  "action": {
    "action_id": "nutrition_low_glycemic_8w",
    "category": "nutrition",
    "duration_weeks": 8,
    "target_mechanisms": [
      "postprandial_glucose_variability",
      "insulin_resistance"
    ],
    "monitoring_markers": [
      "fasting_glucose",
      "hba1c",
      "weight",
      "waist_circumference"
    ]
  },
  "transition_hypothesis": {
    "expected_direction": {
      "fasting_glucose": "decrease_possible",
      "postprandial_glucose": "decrease_possible",
      "weight": "slight_decrease_possible"
    },
    "uncertainty_level": "moderate",
    "time_window_weeks": 8,
    "limitations": [
      "individual_response_varies",
      "not_a_treatment_effect_prediction"
    ]
  },
  "evidence_chain": {
    "overall_strength": "moderate",
    "items": [
      {
        "source_type": "mechanism",
        "description": "Reduced refined carbohydrate intake may reduce postprandial glucose excursions."
      },
      {
        "source_type": "individual_context",
        "description": "Current lifestyle pattern includes high refined carbohydrate intake."
      }
    ]
  },
  "safety_gate": {
    "passed": true,
    "red_flags": [],
    "notes": [
      "not_medical_advice",
      "human_review_required_in_clinical_context"
    ]
  },
  "feedback_plan": {
    "timepoint_weeks": 8,
    "metrics": [
      "fasting_glucose",
      "hba1c",
      "weight",
      "waist_circumference",
      "symptom_score"
    ]
  }
}

13. 开发者实现原则

原则 1：不要从 chatbot 开始

不要一上来写：

answer = llm.chat(user_question)

应先定义对象：

state_schema = define_state_schema()
action_schema = define_action_schema()
transition_schema = define_transition_schema()
evidence_schema = define_evidence_schema()
feedback_schema = define_feedback_schema()

原则 2：不要把 transition 写成疗效预测

避免：

effect = predict_treatment_effect(state, action)

建议：

transition = estimate_transition_hypothesis(state, action, evidence)

原则 3：系统生物学图谱是机制层，不是完整世界模型

mechanism_graph = build_mechanism_graph(omics_data)

这很重要，但还不够。还需要：

action = define_intervention_action()
transition = estimate_transition_hypothesis(state, action, evidence)
feedback = collect_follow_up_feedback()

原则 4：Evidence object 必须是一等对象

不要只输出建议：

recommendation = generate_recommendation(state)

而要输出：

output = {
    "state": state,
    "action": action,
    "transition_hypothesis": transition,
    "evidence_chain": evidence_chain,
    "safety_gate": safety_gate,
    "feedback_plan": feedback_plan
}

原则 5：必须 human-in-the-loop

医学世界模型不应设计成自动治疗系统。

decision = human_expert_review(model_output)

这应该是核心流程，而不是可选项。

原则 6：没有 feedback，就不是强世界模型

如果系统无法更新：

updated_state = update_state(previous_state, action, feedback)

它就更像一次性推荐系统，而不是医学世界模型。

14. SteeraMed 的工程表达

在这个语境下，SteeraMed 可以被理解为一种可驾驭生物医学世界模型框架。

它的工程重点不是“自动控制人体”，而是把下面这些对象组织起来：

State
Action
Transition Hypothesis
Evidence Chain
Safety Gate
Human Review
Feedback
Audit Log

也可以写成：

class SteerableMedicalWorldModel:
    def observe_state(self, patient_id):
        pass

    def generate_actions(self, state):
        pass

    def run_safety_gate(self, state, action):
        pass

    def build_evidence_chain(self, state, action):
        pass

    def estimate_transition(self, state, action, evidence):
        pass

    def request_human_review(self, candidates):
        pass

    def collect_feedback(self, selected_action):
        pass

    def update_model(self, state, action, feedback):
        pass

    def write_audit_log(self, record):
        pass

这比“一个医疗 AI 聊天机器人”复杂得多，也更接近医学真正需要的系统形态。

15. 总结：系统生物学是机制层，医学世界模型是行动推演层

最后总结一下。

系统生物学非常重要，它帮助我们理解生命系统的网络结构、动态调控和机制关系。

但从工程角度看，系统生物学模型通常还不是完整的医学世界模型。

医学世界模型需要把下面几个对象连起来：

individual state
intervention action
mechanism-informed evidence
transition hypothesis
safety gate
human review
longitudinal feedback
audit log

所以，二者不是替代关系，而是层级关系：

Systems biology:
    mechanism understanding

Medical world model:
    mechanism-informed action simulation

Steerable medical world model:
    goal-directed, evidence-bounded, feedback-calibrated intervention reasoning

中文表达就是：

系统生物学让我们理解生命系统；医学世界模型让这种理解进入状态—动作—转移—反馈的推演过程；可驾驭医学世界模型进一步让这个过程具备目标、边界、复核和校准能力。

这也是为什么，在系统生物学已经非常重要的前提下，医学 AI 仍然需要医学世界模型。

参考文献与延伸阅读

  1. Kitano, H. Systems Biology: A Brief Overview. Science, 2002. https://doi.org/10.1126/science.1069492
  2. Kitano, H. Computational systems biology. Nature, 2002. https://doi.org/10.1038/nature01254
  3. Ideker, T., Galitski, T., & Hood, L. A new approach to decoding life: systems biology. Annual Review of Genomics and Human Genetics, 2001. https://doi.org/10.1146/annurev.genom.2.1.343
  4. Barabási, A.-L., Gulbahce, N., & Loscalzo, J. Network medicine: a network-based approach to human disease. Nature Reviews Genetics, 2011. https://doi.org/10.1038/nrg2918
  5. Noble, D. The Music of Life: Biology Beyond Genes. Oxford University Press, 2006.
  6. Ha, D., & Schmidhuber, J. Recurrent World Models Facilitate Policy Evolution. NeurIPS, 2018. https://arxiv.org/abs/1803.10122
  7. LeCun, Y. A Path Towards Autonomous Machine Intelligence. OpenReview, 2022. https://openreview.net/forum?id=BZ5a1r-kVsf
  8. Pearl, J., & Mackenzie, D. The Book of Why: The New Science of Cause and Effect. Basic Books, 2018.
  9. Katsoulakis, E., Wang, Q., Wu, H., et al. Digital twins for health: a scoping review. npj Digital Medicine, 2024. https://doi.org/10.1038/s41746-024-01073-0
  10. Yang, Y., Wang, Z.-Y., Liu, Q., Sun, S., Wang, K., Chellappa, R., Zhou, Z., Yuille, A., Zhu, L., Zhang, Y.-D., & Chen, J. Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning. arXiv:2506.02327, 2025. https://arxiv.org/abs/2506.02327
  11. Xiong, J. World Models for Biomedicine: A Steerability Framework. Preprints.org, 2026. https://doi.org/10.20944/preprints202605.0366.v1
  12. SteeraMed 项目网址：https://SteeraMed.com
  13. Steerable World 项目网址：https://steerable.world

# 人工智能
Logo
AtomGit开源社区

AtomGit 是由开放原子开源基金会联合 CSDN 等生态伙伴共同推出的新一代开源与人工智能协作平台。平台坚持“开放、中立、公益”的理念，把代码托管、模型共享、数据集托管、智能体开发体验和算力服务整合在一起，为开发者提供从开发、训练到部署的一站式体验。

更多推荐

我用 3 天把 AI Agent 接入了酒店系统，踩过的坑全在这了

# 效果验证：接入前后的对比接入完成后，我做了一组对比测试：| 指标 | 接入前（人工查询） | 接入后（AI Agent） | 提升 ||------|-------------------|-------------------|------|| 单次查询耗时 | 3-5 分钟 | 5-10 秒 |### Step 3：在 Agent 中集成接入 MCP 后，你的 Agent 就自动获得了以下

avatar AtomGit开源社区

2026年阿里云 618 Hermes Agent/OpenClaw配置Token Plan部署超全攻略

OpenClaw并非传统的聊天机器人，而是一款本地优先、云端适配的AI自动化代理——它以大语言模型为“大脑”，以Skills插件生态为“手脚”，能理解自然语言指令，自主完成网页操作、邮件管理、文档处理、多平台协同等具象化任务，无需编写复杂的自动化脚本。零代码门槛：通过自然语言下达指令，无需掌握Python/Java等编程技能；多端适配：支持阿里云服务器、本地设备、无影云电脑等多环境部署；生态扩展：

avatar AtomGit开源社区

2026年阿里云 618 Hermes Agent/OpenClaw配置Token Plan搭建保姆分享

OpenClaw并非传统的聊天机器人，而是一款本地优先、云端适配的AI自动化代理——它以大语言模型为“大脑”，以Skills插件生态为“手脚”，能理解自然语言指令，自主完成网页操作、邮件管理、文档处理、多平台协同等具象化任务，无需编写复杂的自动化脚本。零代码门槛：通过自然语言下达指令，无需掌握Python/Java等编程技能；多端适配：支持阿里云服务器、本地设备、无影云电脑等多环境部署；生态扩展：

avatar AtomGit开源社区