Cuzyoung
416 lines
16 KiB
Python
416 lines
16 KiB
Python
"""MathVerse rollout — single-image multimodal math reasoning."""
|
|
from __future__ import annotations
|
|
|
|
import base64
|
|
import json
|
|
import mimetypes
|
|
import os
|
|
from concurrent.futures import ThreadPoolExecutor, as_completed
|
|
|
|
from reflact.envs.mathverse.evaluator import evaluate_item, evaluation_mode, extract_answer
|
|
from reflact.model import chat_student_messages, get_student_backend, is_student_exec_backend
|
|
from reflact.model.codex_harness import prepare_workspace, render_skill_md, run_student_exec
|
|
from reflact.prompts import load_prompt
|
|
|
|
|
|
def _build_system(skill_content: str) -> str:
|
|
if skill_content.strip():
|
|
skill_section = f"## Skill\n{skill_content.strip()}\n\n"
|
|
else:
|
|
skill_section = ""
|
|
return load_prompt("rollout_system", env="mathverse").format(skill_section=skill_section)
|
|
|
|
|
|
def _format_choices(choices: list[dict]) -> str:
|
|
return "\n".join(f"{choice['label']}. {choice['text']}" for choice in choices)
|
|
|
|
|
|
def _build_user_text(
|
|
item: dict,
|
|
*,
|
|
diagnostic_mode: bool = False,
|
|
diagnostic_instruction: str = "",
|
|
diagnostic_trace_context: str = "",
|
|
) -> str:
|
|
parts = []
|
|
if diagnostic_trace_context.strip():
|
|
parts.append(
|
|
"## Previous Codex Trace Snapshot\n"
|
|
"This is a partial transcript from an earlier attempt. Use it as your current reasoning context.\n\n"
|
|
f"{diagnostic_trace_context.strip()}"
|
|
)
|
|
question = str(item.get("question_stem") or item.get("question") or "").strip()
|
|
if question:
|
|
parts.append(f"## Question\n{question}")
|
|
else:
|
|
parts.append("## Question\nRead the full problem statement from the image.")
|
|
|
|
if item.get("is_choice"):
|
|
choices = item.get("choices") or []
|
|
if choices:
|
|
parts.append(f"## Choices\n{_format_choices(choices)}")
|
|
parts.append("Return only the final option label inside <answer>...</answer>.")
|
|
else:
|
|
parts.append("Return only the final mathematical answer inside <answer>...</answer>.")
|
|
|
|
if diagnostic_mode and diagnostic_instruction.strip():
|
|
parts.append(f"## Training Readout\n{diagnostic_instruction.strip()}")
|
|
return "\n\n".join(parts)
|
|
|
|
|
|
def _image_to_data_uri(path: str) -> str:
|
|
mime = mimetypes.guess_type(path)[0] or "image/png"
|
|
with open(path, "rb") as f:
|
|
encoded = base64.b64encode(f.read()).decode("ascii")
|
|
return f"data:{mime};base64,{encoded}"
|
|
|
|
|
|
def _build_messages(
|
|
item: dict,
|
|
skill_content: str,
|
|
image_detail: str,
|
|
*,
|
|
diagnostic_mode: bool = False,
|
|
diagnostic_instruction: str = "",
|
|
diagnostic_trace_context: str = "",
|
|
) -> tuple[list[dict], str, str]:
|
|
system = _build_system(skill_content)
|
|
user_text = _build_user_text(
|
|
item,
|
|
diagnostic_mode=diagnostic_mode,
|
|
diagnostic_instruction=diagnostic_instruction,
|
|
diagnostic_trace_context=diagnostic_trace_context,
|
|
)
|
|
image_url = {"url": _image_to_data_uri(item["image_path"])}
|
|
if image_detail and image_detail != "auto":
|
|
image_url["detail"] = image_detail
|
|
messages = [
|
|
{"role": "system", "content": system},
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "text", "text": user_text},
|
|
{"type": "image_url", "image_url": image_url},
|
|
],
|
|
},
|
|
]
|
|
return messages, system, user_text
|
|
|
|
|
|
def _build_codex_skill(skill_content: str) -> str:
|
|
return render_skill_md(
|
|
skill_content,
|
|
description="Dynamic ReflACT skill for solving the current MathVerse visual math problem.",
|
|
preamble=(
|
|
"Use this skill when solving the current MathVerse problem.\n"
|
|
"Read the image carefully and return the final answer inside <answer>...</answer>."
|
|
),
|
|
)
|
|
|
|
|
|
def _run_codex_once(
|
|
*,
|
|
pred_dir: str,
|
|
item: dict,
|
|
skill_content: str,
|
|
model: str,
|
|
timeout: int,
|
|
image_detail: str,
|
|
diagnostic_mode: bool = False,
|
|
diagnostic_instruction: str = "",
|
|
diagnostic_trace_context: str = "",
|
|
previous_response: str = "",
|
|
) -> tuple[str, str, str, str]:
|
|
user_text = _build_user_text(
|
|
item,
|
|
diagnostic_mode=diagnostic_mode,
|
|
diagnostic_instruction=diagnostic_instruction,
|
|
diagnostic_trace_context=diagnostic_trace_context,
|
|
)
|
|
task_parts = [user_text]
|
|
if previous_response:
|
|
task_parts.append(
|
|
"## Previous Attempt\n"
|
|
f"{previous_response}\n\n"
|
|
"Re-check the diagram and the mathematical constraints. Correct the final answer if needed."
|
|
)
|
|
task_text = "\n\n".join(task_parts)
|
|
skill_md = _build_codex_skill(skill_content)
|
|
work_dir = os.path.join(pred_dir, "codex_exec")
|
|
prepare_workspace(
|
|
work_dir=work_dir,
|
|
skill_md=skill_md,
|
|
task_text=task_text,
|
|
images=[item["image_path"]],
|
|
)
|
|
prompt = (
|
|
"Use the `reflact-student` skill available in this workspace.\n"
|
|
"Read `task.md`, inspect the attached image, solve the problem, and return only the final answer inside <answer>...</answer>."
|
|
)
|
|
final_message, raw = run_student_exec(
|
|
work_dir=work_dir,
|
|
prompt=prompt,
|
|
model=model,
|
|
timeout=timeout,
|
|
images=[item["image_path"]],
|
|
)
|
|
return final_message or raw, raw, skill_md, task_text
|
|
|
|
|
|
def process_one(
|
|
item: dict,
|
|
out_root: str,
|
|
skill_content: str,
|
|
*,
|
|
max_turns: int = 1,
|
|
image_detail: str = "auto",
|
|
judge_model: str = "gpt-5.4",
|
|
judge_max_completion_tokens: int = 256,
|
|
judge_retries: int = 5,
|
|
diagnostic_mode: bool = False,
|
|
diagnostic_instruction: str = "",
|
|
diagnostic_trace_context: str = "",
|
|
) -> dict:
|
|
item_id = str(item["id"])
|
|
result = {
|
|
"id": item_id,
|
|
"question": item["question"],
|
|
"task_type": item.get("task_type") or item.get("question_type") or "mathverse",
|
|
"task_description": item.get("question_stem") or item["question"],
|
|
"hard": 0,
|
|
"soft": 0.0,
|
|
"predicted_answer": "",
|
|
"predicted_label": "",
|
|
"predicted_text": "",
|
|
"response": "",
|
|
"fail_reason": "",
|
|
"agent_ok": False,
|
|
"n_turns": 0,
|
|
"image_path": item["image_path"],
|
|
"question_type": item["question_type"],
|
|
"evaluation_mode": evaluation_mode(),
|
|
"judge_model": judge_model,
|
|
}
|
|
if item.get("is_choice"):
|
|
result["correct_label"] = item["correct_choice"]["label"]
|
|
result["correct_text"] = item["correct_choice"]["text"]
|
|
else:
|
|
result["gold_answers"] = item.get("gold_answers") or [item["answer"]]
|
|
|
|
try:
|
|
pred_dir = os.path.join(out_root, "predictions", item_id)
|
|
os.makedirs(pred_dir, exist_ok=True)
|
|
|
|
if is_student_exec_backend():
|
|
from reflact.model import azure_openai as _llm
|
|
|
|
response = ""
|
|
conversation: list[dict] = [
|
|
{"role": "user", "content": f"{item['question']}\n\n[image] {os.path.basename(item['image_path'])}"}
|
|
]
|
|
system_prompt = ""
|
|
user_text = ""
|
|
for turn in range(max_turns):
|
|
response, raw, system_prompt, user_text = _run_codex_once(
|
|
pred_dir=pred_dir,
|
|
item=item,
|
|
skill_content=skill_content,
|
|
model=_llm.STUDENT_DEPLOYMENT,
|
|
timeout=120,
|
|
image_detail=image_detail,
|
|
diagnostic_mode=diagnostic_mode if turn == 0 else False,
|
|
diagnostic_instruction=diagnostic_instruction if turn == 0 else "",
|
|
diagnostic_trace_context=diagnostic_trace_context if turn == 0 else "",
|
|
previous_response=response if turn > 0 else "",
|
|
)
|
|
conversation.append({"type": "message", "turn": turn + 1, "content": response})
|
|
if extract_answer(response):
|
|
break
|
|
|
|
result["response"] = response
|
|
result["agent_ok"] = True
|
|
result["n_turns"] = len(conversation) - 1
|
|
with open(os.path.join(pred_dir, "student_system_prompt.txt"), "w", encoding="utf-8") as f:
|
|
f.write(system_prompt)
|
|
with open(os.path.join(pred_dir, "student_user_prompt.txt"), "w", encoding="utf-8") as f:
|
|
f.write(user_text)
|
|
else:
|
|
messages, system_prompt, user_text = _build_messages(
|
|
item,
|
|
skill_content,
|
|
image_detail,
|
|
diagnostic_mode=diagnostic_mode,
|
|
diagnostic_instruction=diagnostic_instruction,
|
|
diagnostic_trace_context=diagnostic_trace_context,
|
|
)
|
|
response = ""
|
|
conversation = [
|
|
{"role": "user", "content": f"{user_text}\n\n[image] {os.path.basename(item['image_path'])}"}
|
|
]
|
|
for turn in range(max_turns):
|
|
if turn == 0:
|
|
resp_text, _ = chat_student_messages(
|
|
messages=messages,
|
|
max_completion_tokens=1024,
|
|
retries=5,
|
|
stage="rollout",
|
|
)
|
|
else:
|
|
refinement_text = (
|
|
f"Your previous answer was:\n{response}\n\n"
|
|
"Re-check the diagram and the mathematical constraints. "
|
|
"If needed, correct your answer. Output only the final answer inside <answer>...</answer>."
|
|
)
|
|
refinement_messages = [
|
|
messages[0],
|
|
messages[1],
|
|
{"role": "assistant", "content": response},
|
|
{"role": "user", "content": refinement_text},
|
|
]
|
|
resp_text, _ = chat_student_messages(
|
|
messages=refinement_messages,
|
|
max_completion_tokens=768,
|
|
retries=5,
|
|
stage="rollout",
|
|
)
|
|
response = resp_text
|
|
conversation.append({"type": "message", "turn": turn + 1, "content": resp_text})
|
|
if extract_answer(resp_text):
|
|
break
|
|
|
|
result["response"] = response
|
|
result["agent_ok"] = True
|
|
result["n_turns"] = len(conversation) - 1
|
|
with open(os.path.join(pred_dir, "student_system_prompt.txt"), "w", encoding="utf-8") as f:
|
|
f.write(system_prompt)
|
|
with open(os.path.join(pred_dir, "student_user_prompt.txt"), "w", encoding="utf-8") as f:
|
|
f.write(user_text)
|
|
|
|
eval_result = evaluate_item(
|
|
item=item,
|
|
prediction_text=result["response"],
|
|
judge_model=judge_model,
|
|
max_completion_tokens=judge_max_completion_tokens,
|
|
retries=judge_retries,
|
|
)
|
|
result["evaluation_mode"] = eval_result["evaluation_mode"]
|
|
result["judge_raw"] = eval_result.get("judge_raw", "")
|
|
result["judge_reason"] = eval_result.get("judge_reason", "")
|
|
result["matched_gold"] = eval_result.get("matched_gold", "")
|
|
|
|
if item.get("is_choice"):
|
|
result["predicted_label"] = eval_result["predicted_label"]
|
|
result["predicted_text"] = eval_result["predicted_text"]
|
|
result["predicted_answer"] = eval_result["predicted_answer"]
|
|
result["hard"] = int(eval_result["em"])
|
|
result["soft"] = eval_result["f1"]
|
|
if not result["hard"]:
|
|
result["fail_reason"] = (
|
|
f"choice=0: predicted '{eval_result['predicted_label'] or eval_result['predicted_answer']}' "
|
|
f"but expected '{eval_result['correct_label']}'"
|
|
)
|
|
eval_detail = (
|
|
f"[EVALUATION RESULT]\n"
|
|
f"Question: {item['question_for_eval']}\n"
|
|
f"Predicted label: {eval_result['predicted_label']!r}\n"
|
|
f"Predicted text: {eval_result['predicted_text']!r}\n"
|
|
f"Correct label: {eval_result['correct_label']!r}\n"
|
|
f"Correct text: {eval_result['correct_text']!r}\n"
|
|
f"Exact Match: {eval_result['em']}"
|
|
)
|
|
else:
|
|
result["predicted_answer"] = eval_result["predicted_answer"]
|
|
result["hard"] = int(eval_result["em"])
|
|
result["soft"] = eval_result["f1"]
|
|
if not result["hard"]:
|
|
result["fail_reason"] = (
|
|
f"judge=0: predicted '{eval_result['predicted_answer']}' "
|
|
f"but expected '{item['answer']}' ({eval_result.get('judge_reason', '')})"
|
|
)
|
|
eval_detail = (
|
|
f"[EVALUATION RESULT]\n"
|
|
f"Question: {item['question_for_eval']}\n"
|
|
f"Predicted answer: {eval_result['predicted_answer']!r}\n"
|
|
f"Gold answer: {item['answer']!r}\n"
|
|
f"Judge correct: {eval_result['em']}\n"
|
|
f"Judge reason: {eval_result.get('judge_reason', '')}\n"
|
|
f"String F1: {eval_result.get('string_f1', 0.0):.4f}"
|
|
)
|
|
|
|
conversation.append({"role": "system", "content": eval_detail})
|
|
with open(os.path.join(pred_dir, "conversation.json"), "w", encoding="utf-8") as f:
|
|
json.dump(conversation, f, ensure_ascii=False, indent=2)
|
|
except Exception as e: # noqa: BLE001
|
|
result["fail_reason"] = f"error: {e}"
|
|
return result
|
|
|
|
|
|
def run_batch(
|
|
items: list[dict],
|
|
out_root: str,
|
|
skill_content: str,
|
|
*,
|
|
max_turns: int = 1,
|
|
workers: int = 32,
|
|
image_detail: str = "auto",
|
|
judge_model: str = "gpt-5.4",
|
|
judge_max_completion_tokens: int = 256,
|
|
judge_retries: int = 5,
|
|
diagnostic_mode: bool = False,
|
|
diagnostic_instruction: str = "",
|
|
diagnostic_trace_context_by_id: dict[str, str] | None = None,
|
|
) -> list[dict]:
|
|
results_path = os.path.join(out_root, "results.jsonl")
|
|
os.makedirs(out_root, exist_ok=True)
|
|
|
|
expected_eval_mode = evaluation_mode()
|
|
done_ids: set[str] = set()
|
|
existing: list[dict] = []
|
|
rewrite_results = False
|
|
if os.path.exists(results_path):
|
|
with open(results_path, encoding="utf-8") as f:
|
|
for line in f:
|
|
try:
|
|
row = json.loads(line)
|
|
if row.get("evaluation_mode") != expected_eval_mode:
|
|
rewrite_results = True
|
|
continue
|
|
done_ids.add(str(row["id"]))
|
|
existing.append(row)
|
|
except Exception:
|
|
rewrite_results = True
|
|
|
|
pending = [item for item in items if str(item["id"]) not in done_ids]
|
|
if not pending and not rewrite_results:
|
|
return existing
|
|
|
|
results = list(existing)
|
|
file_mode = "w" if rewrite_results else "a"
|
|
with open(results_path, file_mode, encoding="utf-8") as outf, ThreadPoolExecutor(max_workers=workers) as ex:
|
|
if rewrite_results:
|
|
for row in existing:
|
|
outf.write(json.dumps(row, ensure_ascii=False) + "\n")
|
|
futs = {
|
|
ex.submit(
|
|
process_one,
|
|
item,
|
|
out_root,
|
|
skill_content,
|
|
max_turns=max_turns,
|
|
image_detail=image_detail,
|
|
judge_model=judge_model,
|
|
judge_max_completion_tokens=judge_max_completion_tokens,
|
|
judge_retries=judge_retries,
|
|
diagnostic_mode=diagnostic_mode,
|
|
diagnostic_instruction=diagnostic_instruction,
|
|
diagnostic_trace_context=(diagnostic_trace_context_by_id or {}).get(str(item["id"]), ""),
|
|
): item
|
|
for item in pending
|
|
}
|
|
for fut in as_completed(futs):
|
|
row = fut.result()
|
|
results.append(row)
|
|
outf.write(json.dumps(row, ensure_ascii=False) + "\n")
|
|
outf.flush()
|
|
return results
|