목표 스택과 백트래킹

목표 스택

goal_stack = []

def push(goal):
    goal_stack.append(goal)

def pop():
    return goal_stack.pop() if goal_stack else None

def current():
    return goal_stack[-1] if goal_stack else None

# --- demo ---
push('write the report')
push('collect the data')
print(f'Current goal: {current()}')
print(f'Popped: {pop()}')
print(f'Current goal after pop: {current()}')

Example: Refactoring Workflow

push('Refactor auth')
while current():
    g = current()
    if g == 'Refactor auth':
        if not done('add_oauth_dep'):
            push('Add OAuth dependency')
        elif not done('replace_login'):
            push('Replace login endpoint')
        else:
            pop()   # done
    elif g == 'Add OAuth dependency':
        # ...actually do the work...
        mark_done('add_oauth_dep')
        pop()

백트래킹

Backtracking Example

def attempt(goal):
    for approach in [oauth, saml, custom_token]:
        try:
            return run_with(goal, approach)
        except FailedException:
            continue
    raise NoApproachWorked(goal)

시도한 접근 방식 추적

{
    'goal_id': 'refactor-auth',
    'tried': ['oauth', 'saml'],
    'remaining_options': ['custom_token']
}

목표 선택기로서의 LLM

next_goal = llm.invoke(f'Current goal: {current()}. Done so far: {done_list}. What sub-goal next?').content
push(next_goal)

사전 조건과 결과

action = {
    'name': 'replace_login',
    'preconditions': ['oauth_dep_installed'],
    'effects': ['login_endpoint_replaced']
}

계획과 행동의 반복 과정

기호 기반 방식과 LLM의 결합

막다른 길

if no_progress_in_n_steps(5):
    pop_to_parent()
    try_different_approach()

백트래킹 깊이 제한

MAX_BACKTRACKS = 10
if backtrack_count >= MAX_BACKTRACKS:
    escalate_to_human()

사용자에게 백트래킹 알리기

백트래킹 발동 조건

복습