AI 에이전트 평가: 에이전트 트레이스의 인간 어노테이션 완벽 가이드

pip install --upgrade potato-annotation

{
  "trace_id": "trace_001",
  "task": "What is the capital of Australia and what is its population?",
  "trace": [
    {"type": "thought", "content": "I need to find the capital of Australia and its population. Let me search for this."},
    {"type": "action", "content": "search", "action_input": "capital of Australia"},
    {"type": "observation", "content": "Canberra is the capital city of Australia. It was chosen as the capital in 1908 as a compromise between Sydney and Melbourne."},
    {"type": "thought", "content": "The capital is Canberra. Now I need to find its population."},
    {"type": "action", "content": "search", "action_input": "Canberra population 2025"},
    {"type": "observation", "content": "Canberra has a population of approximately 467,000 as of 2025, making it the eighth-largest city in Australia."},
    {"type": "thought", "content": "I now have both pieces of information. The capital of Australia is Canberra with a population of approximately 467,000."},
    {"type": "action", "content": "finish", "action_input": "The capital of Australia is Canberra, with a population of approximately 467,000 as of 2025."}
  ],
  "ground_truth": "Canberra, approximately 467,000"
}

{
  "trace_id": "oai_001",
  "task": "Find cheap flights from NYC to London",
  "messages": [
    {"role": "user", "content": "Find cheap flights from NYC to London"},
    {"role": "assistant", "content": null, "tool_calls": [{"function": {"name": "search_flights", "arguments": "{\"from\": \"NYC\", \"to\": \"LHR\"}"}}]},
    {"role": "tool", "name": "search_flights", "content": "{\"flights\": [{\"airline\": \"BA\", \"price\": 450}, {\"airline\": \"AA\", \"price\": 520}]}"},
    {"role": "assistant", "content": "I found flights from NYC to London. The cheapest is British Airways at $450."}
  ]
}

annotation_task_name: "ReAct Agent Evaluation"
task_dir: "."
 
data_files:
  - "data/traces.jsonl"
 
item_properties:
  id_key: trace_id
  text_key: task
 
# --- Agentic annotation settings ---
agentic:
  enabled: true
  trace_converter: react
  display_type: agent_trace
 
  agent_trace_display:
    colors:
      thought: "#6E56CF"
      action: "#3b82f6"
      observation: "#22c55e"
      error: "#ef4444"
    collapse_observations: true
    collapse_threshold: 400
    show_step_numbers: true
    show_timestamps: false
    render_json: true
    syntax_highlight: true

annotation_schemes:
  # --- Trace-level schemas ---
 
  # 1. Task success (the most important metric)
  - annotation_type: radio
    name: task_success
    description: "Did the agent successfully complete the task?"
    labels:
      - "Success"
      - "Partial Success"
      - "Failure"
    label_requirement:
      required: true
    sequential_key_binding: true
 
  # 2. Answer correctness (if the task has a ground truth)
  - annotation_type: radio
    name: answer_correctness
    description: "Is the agent's final answer factually correct?"
    labels:
      - "Correct"
      - "Partially Correct"
      - "Incorrect"
      - "Cannot Determine"
    label_requirement:
      required: true
 
  # 3. Efficiency rating
  - annotation_type: likert
    name: efficiency
    description: "Did the agent use an efficient path to the answer?"
    min: 1
    max: 5
    labels:
      1: "Very Inefficient (many unnecessary steps)"
      3: "Average"
      5: "Optimal (no wasted steps)"
 
  # 4. Free-text notes
  - annotation_type: text
    name: evaluator_notes
    description: "Any additional observations"
    label_requirement:
      required: false
 
  # --- Step-level schemas ---
 
  # 5. Per-step correctness
  - annotation_type: per_turn_rating
    name: step_correctness
    target: agentic_steps
    description: "Was this step correct and useful?"
    rating_type: radio
    labels:
      - "Correct"
      - "Partially Correct"
      - "Incorrect"
      - "Unnecessary"
 
  # 6. Per-step error type (only shown when step is not correct)
  - annotation_type: per_turn_rating
    name: error_type
    target: agentic_steps
    description: "What type of error occurred?"
    rating_type: multiselect
    labels:
      - "Wrong tool/action"
      - "Wrong arguments"
      - "Hallucinated information"
      - "Reasoning error"
      - "Redundant step"
      - "Premature termination"
      - "Other"
    conditional:
      show_when:
        step_correctness: ["Partially Correct", "Incorrect", "Unnecessary"]

output_annotation_dir: "output/"
export_annotation_format: "jsonl"
 
# Optional: also export to Parquet for analysis
parquet_export:
  enabled: true
  output_dir: "output/parquet/"
  compression: zstd

annotation_task_name: "ReAct Agent Evaluation"
task_dir: "."
 
data_files:
  - "data/traces.jsonl"
 
item_properties:
  id_key: trace_id
  text_key: task
 
agentic:
  enabled: true
  trace_converter: react
  display_type: agent_trace
  agent_trace_display:
    colors:
      thought: "#6E56CF"
      action: "#3b82f6"
      observation: "#22c55e"
      error: "#ef4444"
    collapse_observations: true
    collapse_threshold: 400
    show_step_numbers: true
    render_json: true
    syntax_highlight: true
 
annotation_schemes:
  - annotation_type: radio
    name: task_success
    description: "Did the agent successfully complete the task?"
    labels: ["Success", "Partial Success", "Failure"]
    label_requirement:
      required: true
    sequential_key_binding: true
 
  - annotation_type: radio
    name: answer_correctness
    description: "Is the agent's final answer factually correct?"
    labels: ["Correct", "Partially Correct", "Incorrect", "Cannot Determine"]
    label_requirement:
      required: true
 
  - annotation_type: likert
    name: efficiency
    description: "Did the agent use an efficient path?"
    min: 1
    max: 5
    labels:
      1: "Very Inefficient"
      3: "Average"
      5: "Optimal"
 
  - annotation_type: text
    name: evaluator_notes
    description: "Any additional observations"
    label_requirement:
      required: false
 
  - annotation_type: per_turn_rating
    name: step_correctness
    target: agentic_steps
    description: "Was this step correct?"
    rating_type: radio
    labels: ["Correct", "Partially Correct", "Incorrect", "Unnecessary"]
 
  - annotation_type: per_turn_rating
    name: error_type
    target: agentic_steps
    description: "Error type"
    rating_type: multiselect
    labels:
      - "Wrong tool/action"
      - "Wrong arguments"
      - "Hallucinated information"
      - "Reasoning error"
      - "Redundant step"
      - "Premature termination"
      - "Other"
    conditional:
      show_when:
        step_correctness: ["Partially Correct", "Incorrect", "Unnecessary"]
 
output_annotation_dir: "output/"
export_annotation_format: "jsonl"
 
parquet_export:
  enabled: true
  output_dir: "output/parquet/"
  compression: zstd

potato start config.yaml -p 8000

import pandas as pd
import json
 
# Load annotations
annotations = []
with open("output/annotations.jsonl") as f:
    for line in f:
        annotations.append(json.loads(line))
 
df = pd.DataFrame(annotations)
 
# Task success rate
success_counts = df.groupby("annotations").apply(
    lambda x: x.iloc[0]["annotations"]["task_success"]
).value_counts()
print("Task Success Distribution:")
print(success_counts)
 
# Average efficiency rating
efficiency_scores = [
    a["annotations"]["efficiency"]
    for a in annotations
    if "efficiency" in a["annotations"]
]
print(f"\nAverage Efficiency: {sum(efficiency_scores) / len(efficiency_scores):.2f}")

# Collect all step-level errors
error_counts = {}
for ann in annotations:
    step_errors = ann["annotations"].get("error_type", {})
    for step_idx, errors in step_errors.items():
        for error in errors:
            error_counts[error] = error_counts.get(error, 0) + 1
 
print("Error Type Distribution:")
for error, count in sorted(error_counts.items(), key=lambda x: -x[1]):
    print(f"  {error}: {count}")

import duckdb
 
# Overall success rate
result = duckdb.sql("""
    SELECT value, COUNT(*) as count
    FROM 'output/parquet/annotations.parquet'
    WHERE schema_name = 'task_success'
    GROUP BY value
    ORDER BY count DESC
""")
print(result)

annotation_task_config:
  total_annotations_per_instance: 3
  assignment_strategy: random

annotation_schemes:
  - preset: agent_task_success
  - preset: agent_step_correctness
  - preset: agent_error_taxonomy
  - preset: agent_efficiency

phases:
  training:
    enabled: true
    data_file: "data/training_traces.jsonl"
    passing_criteria:
      min_correct: 4
      total_questions: 5

agentic:
  enabled: true
  trace_converter: openai
  display_type: agent_trace

agentic:
  enabled: true
  trace_converter: anthropic
  display_type: agent_trace

agentic:
  enabled: true
  trace_converter: multi_agent
  display_type: agent_trace
  multi_agent:
    agent_converters:
      researcher: react
      writer: anthropic
      reviewer: openai

agentic:
  enabled: true
  trace_converter: webarena
  display_type: web_agent
  web_agent_display:
    screenshot_max_width: 900
    overlay:
      enabled: true
    filmstrip:
      enabled: true