Agentic-Eval

Generate → Evaluate → Critique → Refine → Output
    ↑                              │
    └──────────────────────────────┘

def reflect_and_refine(task: str, criteria: list[str], max_iterations: int = 3) -> str:
    """Generate with reflection loop."""
    output = llm(f"Complete this task:\n{task}")
    
    for i in range(max_iterations):
        # Self-critique
        critique = llm(f"""
        Evaluate this output against criteria: {criteria}
        Output: {output}
        Rate each: PASS/FAIL with feedback as JSON.
        """)
        
        critique_data = json.loads(critique)
        all_pass = all(c["status"] == "PASS" for c in critique_data.values())
        if all_pass:
            return output
        
        # Refine based on critique
        failed = {k: v["feedback"] for k, v in critique_data.items() if v["status"] == "FAIL"}
        output = llm(f"Improve to address: {failed}\nOriginal: {output}")
    
    return output

class EvaluatorOptimizer:
    def __init__(self, score_threshold: float = 0.8):
        self.score_threshold = score_threshold
    
    def generate(self, task: str) -> str:
        return llm(f"Complete: {task}")
    
    def evaluate(self, output: str, task: str) -> dict:
        return json.loads(llm(f"""
        Evaluate output for task: {task}
        Output: {output}
        Return JSON: {{"overall_score": 0-1, "dimensions": {{"accuracy": ..., "clarity": ...}}}}
        """))
    
    def optimize(self, output: str, feedback: dict) -> str:
        return llm(f"Improve based on feedback: {feedback}\nOutput: {output}")
    
    def run(self, task: str, max_iterations: int = 3) -> str:
        output = self.generate(task)
        for _ in range(max_iterations):
            evaluation = self.evaluate(output, task)
            if evaluation["overall_score"] >= self.score_threshold:
                break
            output = self.optimize(output, evaluation)
        return output

class CodeReflector:
    def reflect_and_fix(self, spec: str, max_iterations: int = 3) -> str:
        code = llm(f"Write Python code for: {spec}")
        tests = llm(f"Generate pytest tests for: {spec}\nCode: {code}")
        
        for _ in range(max_iterations):
            result = run_tests(code, tests)
            if result["success"]:
                return code
            code = llm(f"Fix error: {result['error']}\nCode: {code}")
        return code

def evaluate_outcome(task: str, output: str, expected: str) -> str:
    return llm(f"Does output achieve expected outcome? Task: {task}, Expected: {expected}, Output: {output}")

def llm_judge(output_a: str, output_b: str, criteria: str) -> str:
    return llm(f"Compare outputs A and B for {criteria}. Which is better and why?")

RUB