2nd/10_Wiki/Topics/Domain_Programming/AI_and_ML/Refinement.md

id, title, category, status, canonical_id, aliases, duplicate_of, source_trust_level, confidence_score, verification_status, tags, raw_sources, last_reinforced, github_commit, tech_stack

id	title	category	status	canonical_id	aliases	duplicate_of	source_trust_level	confidence_score	verification_status	tags	raw_sources	last_reinforced	github_commit	tech_stack
wiki-2026-0508-refinement	Refinement	10_Wiki/Topics	verified	self	Iterative-Refinement Self-Refine Type-Refinement	none	A	0.9	applied	llm iteration types design		2026-05-10	pending	language framework python anthropic-sdk

Refinement

매 한 줄

"매 첫 시도는 draft, 매 refinement는 product". Refinement는 초안을 critique → revise loop로 다듬어 quality를 끌어올리는 patterns의 family — LLM self-refine, type narrowing, design iteration 모두 매 같은 핵심 idea를 공유.

매 핵심

매 LLM Self-Refine (2024 Madaan et al. → 2026 mainstream)

• Generate → Critique → Refine loop. Single model이 매 세 role을 모두 수행.
• 매 효과: math, code, dialog 매 +5–20% accuracy without extra training.
• Reflexion (Shinn 2023)은 verbal RL — 매 episode 끝에 매 self-critique를 episodic memory로 저장.
• 2026 standard: Claude Opus 4.7 / GPT-5 매 native "extended thinking" mode가 매 refine을 internal로 흡수 → external loop는 매 high-stakes (legal, medical) 에서만.

매 Type Refinement (TypeScript / Flow / Python typing)

• Narrowing: union type 의 매 instance를 specific subtype 으로 좁힘 (typeof, instanceof, discriminated union).
• Refinement type: predicate-attached type — {x: number | x > 0}. Liquid Haskell, F* 매 사용.
• 2026 TS 5.x: satisfies operator + control-flow analysis 매 강력 — 매 manual cast 의 거의 elimination.

매 Design / Spec Refinement

• Stepwise refinement (Wirth 1971) — abstract spec → concrete implementation을 매 단계적으로.
• BDD (Given-When-Then) 매 modern incarnation.
• AI-aided: spec → Claude → multiple impl candidates → human picks → refine.

매 응용

1. RAG answer 의 self-refine으로 hallucination ↓.
2. Code generation 매 compile error → refine loop.
3. TS API 의 progressive type narrowing.
4. Product spec 의 PM ↔ AI iterative tightening.

💻 패턴

Self-Refine loop (Anthropic SDK)

from anthropic import Anthropic

client = Anthropic()
MODEL = "claude-opus-4-7"

def self_refine(task: str, max_iter: int = 3) -> str:
    answer = client.messages.create(
        model=MODEL, max_tokens=2048,
        messages=[{"role": "user", "content": task}],
    ).content[0].text

    for i in range(max_iter):
        critique = client.messages.create(
            model=MODEL, max_tokens=1024,
            system="You are a strict critic. List concrete flaws or reply 'NO_ISSUES'.",
            messages=[{"role": "user", "content": f"Task: {task}\n\nDraft:\n{answer}"}],
        ).content[0].text

        if "NO_ISSUES" in critique:
            return answer

        answer = client.messages.create(
            model=MODEL, max_tokens=2048,
            messages=[{"role": "user",
                       "content": f"Task: {task}\nDraft: {answer}\nCritique: {critique}\nRevise."}],
        ).content[0].text
    return answer

Reflexion-style episodic memory

class Reflexion:
    def __init__(self):
        self.memory: list[str] = []  # accumulated lessons

    def step(self, task: str) -> str:
        ctx = "\n".join(f"- {m}" for m in self.memory[-5:])
        attempt = llm(f"Task: {task}\nPast lessons:\n{ctx}\nAct.")
        feedback = environment(attempt)
        if not feedback.success:
            lesson = llm(f"Why did this fail? Task: {task}\nAttempt: {attempt}\nFeedback: {feedback}")
            self.memory.append(lesson)
        return attempt

TypeScript discriminated union narrowing

type Result<T> =
  | { kind: 'ok'; value: T }
  | { kind: 'err'; error: Error };

function unwrap<T>(r: Result<T>): T {
  if (r.kind === 'err') throw r.error;  // narrow → 'ok' branch
  return r.value;  // typed as T, no cast
}

Python TypeGuard refinement

from typing import TypeGuard

def is_str_list(x: list[object]) -> TypeGuard[list[str]]:
    return all(isinstance(i, str) for i in x)

def join(items: list[object]) -> str:
    if is_str_list(items):
        return ", ".join(items)  # narrowed
    raise TypeError("not str list")

Compile-error refine loop (code generation)

def codegen_refine(spec: str, max_iter=5):
    code = llm(f"Write Python for: {spec}")
    for _ in range(max_iter):
        ok, err = run_pytest(code)
        if ok: return code
        code = llm(f"Spec: {spec}\nCode: {code}\nFailing: {err}\nFix.")
    raise RuntimeError("refinement budget exhausted")

Best-of-N + judge (ensemble refinement)

def best_of_n(prompt: str, n: int = 5) -> str:
    candidates = [llm(prompt, temperature=1.0) for _ in range(n)]
    ranking = llm(f"Pick best of these:\n{candidates}\nReturn index 0..{n-1}")
    return candidates[int(ranking.strip())]

매 결정 기준

상황	Approach
Single-shot good enough (chat)	No refine — extra cost
High-stakes (legal/medical)	External self-refine + human review
Code with tests	Compile/test-driven refine
Long agentic task	Reflexion (episodic memory)
Reasoning math	extended thinking (native) — already refine internally
TS API design	Narrowing + satisfies

기본값: native extended thinking 우선 → 부족하면 external self-refine 1–2 iter.

🔗 Graph

• 부모: Iteration
• 변형: Reflexion · Self-Consistency · Best-of-N
• 응용: RAG · Code-Generation
• Adjacent: TypeScript 타입 시스템 (TypeScript Type System) · Stepwise-Refinement · BDD

🤖 LLM 활용

언제: high-stakes output, agentic loops, code with verifiable feedback. 언제 X: 매 latency-sensitive UX, 매 simple chat — extra latency × cost는 매 안 맞음.

❌ 안티패턴

• Infinite refine loop: max_iter 의 hard cap 의 X → cost explosion.
• Same-model critique only: 매 critic = generator인 경우 같은 blind spot. Mix models (Opus critic, Sonnet generator).
• Refine without termination signal: "NO_ISSUES" 같은 매 explicit stop 의 부재 → 매 endless tweaking.
• Type assertion 으로 narrow: TS 매 as 사용은 매 refinement 의 X — 매 unsafe cast.

🧪 검증 / 중복

• Verified (Madaan 2024 Self-Refine, Shinn 2023 Reflexion, TS handbook narrowing).
• 신뢰도 A.

🕓 Changelog

날짜	변경
2026-05-08	Phase 1
2026-05-10	Manual cleanup — full rewrite covering LLM self-refine, type narrowing, design iteration