Initial commit
This commit is contained in:
Cuzyoung
@@ -0,0 +1,5 @@
|
||||
"""MathVerse environment package."""
|
||||
|
||||
from skillopt.envs.mathverse.adapter import MathVerseAdapter
|
||||
|
||||
__all__ = ["MathVerseAdapter"]
|
||||
@@ -0,0 +1,280 @@
|
||||
"""MathVerse environment adapter for ReflACT."""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
|
||||
from skillopt.datasets.base import BatchSpec
|
||||
from skillopt.envs.base import EnvAdapter
|
||||
from skillopt.envs.mathverse.dataloader import MathVerseDataLoader
|
||||
from skillopt.envs.mathverse.rollout import run_batch
|
||||
from skillopt.gradient.deep_probe import generate_deep_probe_instruction
|
||||
from skillopt.gradient.reflect import run_minibatch_reflect
|
||||
from skillopt.model import get_student_backend
|
||||
|
||||
|
||||
class MathVerseAdapter(EnvAdapter):
|
||||
"""MathVerse adapter."""
|
||||
|
||||
def build_reference_text(self, item: dict) -> str:
|
||||
if not self.use_text_dominant_reference:
|
||||
return ""
|
||||
question = str(item.get("text_dominant_question") or "").strip()
|
||||
if not question:
|
||||
return ""
|
||||
return f"## Reference Full Question\n{question}"
|
||||
|
||||
def get_reference_metadata(self, item: dict) -> dict:
|
||||
if not self.use_text_dominant_reference:
|
||||
return {"fields": [], "preview": ""}
|
||||
question = str(item.get("text_dominant_question") or "").strip()
|
||||
if not question:
|
||||
return {"fields": [], "preview": ""}
|
||||
return {
|
||||
"fields": ["text_dominant_question"],
|
||||
"preview": question[:400],
|
||||
}
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
split_dir: str = "",
|
||||
data_root: str = "",
|
||||
problem_version: str = "Text Lite",
|
||||
use_text_dominant_reference: bool = False,
|
||||
max_turns: int = 1,
|
||||
workers: int = 16,
|
||||
analyst_workers: int = 16,
|
||||
failure_only: bool = False,
|
||||
minibatch_size: int = 8,
|
||||
edit_budget: int = 4,
|
||||
seed: int = 42,
|
||||
limit: int = 0,
|
||||
image_detail: str = "auto",
|
||||
judge_model: str = "gpt-5.4",
|
||||
judge_max_completion_tokens: int = 256,
|
||||
judge_retries: int = 5,
|
||||
use_deep_reflect: bool = False,
|
||||
deep_reflect_failures: int = 4,
|
||||
deep_reflect_successes: int = 2,
|
||||
) -> None:
|
||||
self.max_turns = max_turns
|
||||
self.workers = workers
|
||||
self.analyst_workers = analyst_workers
|
||||
self.failure_only = failure_only
|
||||
self.minibatch_size = minibatch_size
|
||||
self.edit_budget = edit_budget
|
||||
self.image_detail = image_detail
|
||||
self.judge_model = judge_model
|
||||
self.judge_max_completion_tokens = judge_max_completion_tokens
|
||||
self.judge_retries = judge_retries
|
||||
self.problem_version = problem_version
|
||||
self.use_text_dominant_reference = use_text_dominant_reference
|
||||
self.use_deep_reflect = use_deep_reflect
|
||||
self.deep_reflect_failures = deep_reflect_failures
|
||||
self.deep_reflect_successes = deep_reflect_successes
|
||||
self.dataloader = MathVerseDataLoader(
|
||||
split_dir=split_dir,
|
||||
seed=seed,
|
||||
limit=limit,
|
||||
data_root=data_root,
|
||||
problem_version=problem_version,
|
||||
)
|
||||
|
||||
def setup(self, cfg: dict) -> None:
|
||||
super().setup(cfg)
|
||||
self.dataloader.setup(cfg)
|
||||
|
||||
def get_dataloader(self):
|
||||
return self.dataloader
|
||||
|
||||
def build_env_from_batch(self, batch: BatchSpec, **kwargs):
|
||||
return list(batch.payload or [])
|
||||
|
||||
def build_train_env(self, batch_size: int, seed: int, **kwargs):
|
||||
batch = self.dataloader.build_train_batch(batch_size=batch_size, seed=seed, **kwargs)
|
||||
return self.build_env_from_batch(batch, **kwargs)
|
||||
|
||||
def build_eval_env(self, env_num: int, split: str, seed: int, **kwargs):
|
||||
batch = self.dataloader.build_eval_batch(env_num=env_num, split=split, seed=seed, **kwargs)
|
||||
return self.build_env_from_batch(batch, **kwargs)
|
||||
|
||||
def rollout(
|
||||
self,
|
||||
env_manager,
|
||||
skill_content: str,
|
||||
out_dir: str,
|
||||
**kwargs,
|
||||
) -> list[dict]:
|
||||
items: list[dict] = env_manager
|
||||
return run_batch(
|
||||
items=items,
|
||||
out_root=out_dir,
|
||||
skill_content=skill_content,
|
||||
max_turns=self.max_turns,
|
||||
workers=self.workers,
|
||||
image_detail=self.image_detail,
|
||||
judge_model=self.judge_model,
|
||||
judge_max_completion_tokens=self.judge_max_completion_tokens,
|
||||
judge_retries=self.judge_retries,
|
||||
diagnostic_mode=kwargs.get("diagnostic_mode", False),
|
||||
diagnostic_instruction=kwargs.get("diagnostic_instruction", ""),
|
||||
diagnostic_trace_context_by_id=kwargs.get("diagnostic_trace_context_by_id"),
|
||||
)
|
||||
|
||||
def reflect(
|
||||
self,
|
||||
results: list[dict],
|
||||
skill_content: str,
|
||||
out_dir: str,
|
||||
**kwargs,
|
||||
) -> list[dict | None]:
|
||||
prediction_dir = kwargs.get("prediction_dir", os.path.join(out_dir, "predictions"))
|
||||
patches_dir = kwargs.get("patches_dir", os.path.join(out_dir, "patches"))
|
||||
random_seed = kwargs.get("random_seed")
|
||||
step_buffer_context = kwargs.get("step_buffer_context", "")
|
||||
|
||||
return run_minibatch_reflect(
|
||||
results=results,
|
||||
skill_content=skill_content,
|
||||
prediction_dir=prediction_dir,
|
||||
patches_dir=patches_dir,
|
||||
workers=self.analyst_workers,
|
||||
failure_only=self.failure_only,
|
||||
minibatch_size=self.minibatch_size,
|
||||
edit_budget=self.edit_budget,
|
||||
random_seed=random_seed,
|
||||
error_system=self.get_error_minibatch_prompt(),
|
||||
success_system=self.get_success_minibatch_prompt(),
|
||||
step_buffer_context=step_buffer_context,
|
||||
update_mode=getattr(self, "_cfg", {}).get("skill_update_mode", "patch"),
|
||||
)
|
||||
|
||||
def deep_reflect(
|
||||
self,
|
||||
results: list[dict],
|
||||
skill_content: str,
|
||||
out_dir: str,
|
||||
**kwargs,
|
||||
) -> list[dict | None]:
|
||||
if not self.use_deep_reflect:
|
||||
return []
|
||||
|
||||
env_manager = kwargs.get("env_manager")
|
||||
prediction_dir = kwargs.get("prediction_dir", os.path.join(out_dir, "predictions"))
|
||||
random_seed = kwargs.get("random_seed")
|
||||
step_buffer_context = kwargs.get("step_buffer_context", "")
|
||||
selected_items = self.select_representative_items(
|
||||
results,
|
||||
env_manager if isinstance(env_manager, list) else None,
|
||||
n_failures=self.deep_reflect_failures,
|
||||
n_successes=self.deep_reflect_successes,
|
||||
seed=random_seed,
|
||||
)
|
||||
if not selected_items:
|
||||
return []
|
||||
|
||||
selected_ids = {str(item["id"]) for item in selected_items}
|
||||
selected_results = [row for row in results if str(row.get("id")) in selected_ids]
|
||||
selected_examples = self.attach_reference_context(selected_results, selected_items)
|
||||
codex_backend = get_student_backend() == "codex_exec"
|
||||
if codex_backend:
|
||||
selected_examples = self.attach_codex_probe_context(selected_examples, prediction_dir)
|
||||
selected_metadata = []
|
||||
ref_count = 0
|
||||
for item in selected_items:
|
||||
meta = self.get_reference_metadata(item)
|
||||
if meta["fields"]:
|
||||
ref_count += 1
|
||||
record = {
|
||||
"id": str(item["id"]),
|
||||
"task_type": str(item.get("task_type") or item.get("question_type") or "mathverse"),
|
||||
"reference_fields": meta["fields"],
|
||||
"reference_preview": meta["preview"],
|
||||
}
|
||||
if codex_backend:
|
||||
record["codex_probe_step_count"] = int(
|
||||
next(
|
||||
(row.get("codex_probe_step_count", 0) for row in selected_examples if str(row.get("id")) == str(item["id"])),
|
||||
0,
|
||||
)
|
||||
)
|
||||
selected_metadata.append(record)
|
||||
|
||||
deep_dir = os.path.join(out_dir, "deep_reflect")
|
||||
rollout_dir = os.path.join(deep_dir, "rollout")
|
||||
patches_dir = os.path.join(deep_dir, "patches")
|
||||
os.makedirs(deep_dir, exist_ok=True)
|
||||
print(
|
||||
f" [2b/6 DEEP REFLECT setup] selected={len(selected_items)} "
|
||||
f"reference_fields=text_dominant_question({ref_count}/{len(selected_items)})"
|
||||
)
|
||||
probe = generate_deep_probe_instruction(
|
||||
skill_content=skill_content,
|
||||
items=selected_examples,
|
||||
prediction_dir=prediction_dir,
|
||||
system_prompt=self.get_codex_deep_probe_prompt() if codex_backend else self.get_deep_probe_prompt(),
|
||||
step_buffer_context=step_buffer_context,
|
||||
)
|
||||
if not probe:
|
||||
return []
|
||||
|
||||
targeted_items = selected_items
|
||||
diagnostic_trace_context_by_id: dict[str, str] | None = None
|
||||
if codex_backend:
|
||||
targeted_items, diagnostic_trace_context_by_id, probe = self.resolve_codex_probe_target(
|
||||
selected_items=selected_items,
|
||||
selected_examples=selected_examples,
|
||||
prediction_dir=prediction_dir,
|
||||
probe=probe,
|
||||
)
|
||||
|
||||
with open(os.path.join(deep_dir, "probe.json"), "w", encoding="utf-8") as f:
|
||||
json.dump(
|
||||
{
|
||||
**probe,
|
||||
"reference_summary": {
|
||||
"selected_count": len(selected_items),
|
||||
"field_counts": {
|
||||
"text_dominant_question": ref_count,
|
||||
},
|
||||
},
|
||||
"selected_examples": selected_metadata,
|
||||
},
|
||||
f,
|
||||
ensure_ascii=False,
|
||||
indent=2,
|
||||
)
|
||||
|
||||
deep_results = run_batch(
|
||||
items=targeted_items,
|
||||
out_root=rollout_dir,
|
||||
skill_content=skill_content,
|
||||
max_turns=self.max_turns,
|
||||
workers=min(self.workers, max(len(targeted_items), 1)),
|
||||
image_detail=self.image_detail,
|
||||
judge_model=self.judge_model,
|
||||
judge_max_completion_tokens=self.judge_max_completion_tokens,
|
||||
judge_retries=self.judge_retries,
|
||||
diagnostic_mode=True,
|
||||
diagnostic_instruction=probe["probe_instruction"],
|
||||
diagnostic_trace_context_by_id=diagnostic_trace_context_by_id,
|
||||
)
|
||||
deep_results = self.attach_reference_context(deep_results, targeted_items)
|
||||
return run_minibatch_reflect(
|
||||
results=deep_results,
|
||||
skill_content=skill_content,
|
||||
prediction_dir=os.path.join(rollout_dir, "predictions"),
|
||||
patches_dir=patches_dir,
|
||||
workers=self.analyst_workers,
|
||||
failure_only=self.failure_only,
|
||||
minibatch_size=self.minibatch_size,
|
||||
edit_budget=self.edit_budget,
|
||||
random_seed=random_seed,
|
||||
error_system=self.get_error_minibatch_prompt(),
|
||||
success_system=self.get_success_minibatch_prompt(),
|
||||
step_buffer_context=step_buffer_context,
|
||||
update_mode=getattr(self, "_cfg", {}).get("skill_update_mode", "patch"),
|
||||
)
|
||||
|
||||
def get_task_types(self) -> list[str]:
|
||||
return self.dataloader.get_task_types()
|
||||
@@ -0,0 +1,228 @@
|
||||
"""MathVerse task dataloader."""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
from skillopt.datasets.base import SplitDataLoader
|
||||
|
||||
|
||||
_CHOICE_LABELS = ["A", "B", "C", "D", "E", "F", "G"]
|
||||
_CHOICE_BLOCK_RE = re.compile(r"\bChoices?\s*:\s*", re.IGNORECASE)
|
||||
_CHOICE_ITEM_RE = re.compile(r"([A-G])\s*[:.)]\s*(.*?)(?=(?:\s+[A-G]\s*[:.)])|$)", re.DOTALL)
|
||||
|
||||
|
||||
def _load_json(path: str) -> Any:
|
||||
with open(path, encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
|
||||
|
||||
def _normalize_space(text: Any) -> str:
|
||||
return re.sub(r"\s+", " ", str(text or "").strip())
|
||||
|
||||
|
||||
def _resolve_image_path(raw_path: str, *, data_root: str, source_path: str) -> str:
|
||||
candidates = []
|
||||
if raw_path:
|
||||
if os.path.isabs(raw_path):
|
||||
candidates.append(raw_path)
|
||||
else:
|
||||
if data_root:
|
||||
candidates.append(os.path.join(data_root, raw_path))
|
||||
candidates.append(os.path.join(data_root, "images", raw_path))
|
||||
candidates.append(os.path.join(os.path.dirname(source_path), raw_path))
|
||||
for candidate in candidates:
|
||||
if candidate and os.path.exists(candidate):
|
||||
return os.path.abspath(candidate)
|
||||
return ""
|
||||
|
||||
|
||||
def _split_question_and_choices(question: str) -> tuple[str, list[dict]]:
|
||||
text = str(question or "").strip()
|
||||
match = _CHOICE_BLOCK_RE.search(text)
|
||||
if not match:
|
||||
return text, []
|
||||
|
||||
stem = text[:match.start()].strip()
|
||||
choice_block = text[match.end():].strip()
|
||||
choices: list[dict] = []
|
||||
for idx, m in enumerate(_CHOICE_ITEM_RE.finditer(choice_block)):
|
||||
label = (m.group(1) or _CHOICE_LABELS[idx]).strip().upper()
|
||||
choice_text = _normalize_space(m.group(2))
|
||||
if choice_text:
|
||||
choices.append({"label": label, "text": choice_text})
|
||||
return stem or text, choices
|
||||
|
||||
|
||||
def _build_text_dominant_map(data_root: str) -> dict[str, str]:
|
||||
if not data_root:
|
||||
return {}
|
||||
candidates = [
|
||||
os.path.join(data_root, "testmini.json"),
|
||||
os.path.join(data_root, "data", "testmini.json"),
|
||||
]
|
||||
source_path = next((path for path in candidates if os.path.exists(path)), "")
|
||||
if not source_path:
|
||||
return {}
|
||||
|
||||
raw = _load_json(source_path)
|
||||
if not isinstance(raw, list):
|
||||
return {}
|
||||
|
||||
mapping: dict[str, str] = {}
|
||||
for item in raw:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
if str(item.get("problem_version") or "").strip() != "Text Dominant":
|
||||
continue
|
||||
problem_index = str(item.get("problem_index") or "").strip()
|
||||
question = str(item.get("question") or "").strip()
|
||||
if problem_index and question:
|
||||
mapping[problem_index] = question
|
||||
return mapping
|
||||
|
||||
|
||||
def _normalize_item(
|
||||
item: dict,
|
||||
*,
|
||||
row_idx: int,
|
||||
source_path: str,
|
||||
data_root: str,
|
||||
problem_version: str,
|
||||
text_dominant_map: dict[str, str],
|
||||
) -> dict | None:
|
||||
raw_problem_version = str(item.get("problem_version") or "").strip()
|
||||
if problem_version and raw_problem_version and raw_problem_version != problem_version:
|
||||
return None
|
||||
|
||||
question = str(item.get("question") or "").strip()
|
||||
question_type = str(item.get("question_type") or "").strip()
|
||||
answer = str(item.get("answer") or "").strip()
|
||||
image_rel = str(item.get("image") or "").strip()
|
||||
image_path = _resolve_image_path(image_rel, data_root=data_root, source_path=source_path)
|
||||
if not answer or not image_path:
|
||||
return None
|
||||
|
||||
metadata = item.get("metadata") if isinstance(item.get("metadata"), dict) else {}
|
||||
subject = str(metadata.get("subject") or "").strip()
|
||||
subfield = str(metadata.get("subfield") or "").strip()
|
||||
source = str(metadata.get("source") or "").strip()
|
||||
|
||||
question_stem, choices = _split_question_and_choices(question)
|
||||
is_choice = question_type == "multi-choice" or bool(choices)
|
||||
|
||||
correct_choice = {"label": "", "text": ""}
|
||||
if is_choice:
|
||||
label = str(answer).strip().upper().rstrip(".):")
|
||||
choice_text = ""
|
||||
for choice in choices:
|
||||
if choice["label"].upper() == label:
|
||||
choice_text = choice["text"]
|
||||
break
|
||||
correct_choice = {"label": label, "text": choice_text}
|
||||
|
||||
problem_index = str(item.get("problem_index") or "").strip()
|
||||
sample_index = str(item.get("sample_index") or row_idx + 1).strip()
|
||||
item_id = problem_index or sample_index
|
||||
task_type = subfield or subject or question_type or "mathverse"
|
||||
|
||||
return {
|
||||
"id": item_id,
|
||||
"sample_index": sample_index,
|
||||
"problem_index": problem_index,
|
||||
"problem_version": raw_problem_version or problem_version,
|
||||
"question": question,
|
||||
"question_stem": question_stem,
|
||||
"question_for_eval": str(item.get("question_for_eval") or question).strip(),
|
||||
"question_type": question_type or ("multi-choice" if is_choice else "free-form"),
|
||||
"is_choice": is_choice,
|
||||
"choices": choices,
|
||||
"correct_choice": correct_choice,
|
||||
"answer": answer,
|
||||
"gold_answers": [answer] if answer else [],
|
||||
"image_rel": image_rel,
|
||||
"image_path": image_path,
|
||||
"query_wo": str(item.get("query_wo") or "").strip(),
|
||||
"query_cot": str(item.get("query_cot") or "").strip(),
|
||||
"metadata": {
|
||||
"split": str(metadata.get("split") or "").strip(),
|
||||
"source": source,
|
||||
"subject": subject,
|
||||
"subfield": subfield,
|
||||
},
|
||||
"task_type": task_type,
|
||||
"source_path": os.path.abspath(source_path),
|
||||
"text_dominant_question": str(
|
||||
item.get("text_dominant_question")
|
||||
or text_dominant_map.get(problem_index, "")
|
||||
).strip(),
|
||||
}
|
||||
|
||||
|
||||
class MathVerseDataLoader(SplitDataLoader):
|
||||
"""MathVerse dataloader."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
split_dir: str = "",
|
||||
seed: int = 42,
|
||||
limit: int = 0,
|
||||
data_root: str = "",
|
||||
problem_version: str = "Text Lite",
|
||||
**kwargs,
|
||||
) -> None:
|
||||
super().__init__(split_dir=split_dir, seed=seed, limit=limit)
|
||||
self.data_root = data_root
|
||||
self.problem_version = problem_version
|
||||
self._task_types: list[str] = []
|
||||
self._text_dominant_map = _build_text_dominant_map(data_root)
|
||||
|
||||
def setup(self, cfg: dict) -> None:
|
||||
if not self.data_root:
|
||||
self.data_root = str(cfg.get("data_root") or "")
|
||||
if not self.problem_version:
|
||||
self.problem_version = str(cfg.get("problem_version") or "Text Lite")
|
||||
self._text_dominant_map = _build_text_dominant_map(self.data_root)
|
||||
super().setup(cfg)
|
||||
all_items = self.train_items + self.val_items + self.test_items
|
||||
task_types = {
|
||||
item.get("task_type") or item.get("question_type") or "mathverse"
|
||||
for item in all_items
|
||||
}
|
||||
self._task_types = sorted(str(x) for x in task_types if str(x).strip())
|
||||
|
||||
def get_task_types(self) -> list[str]:
|
||||
return list(self._task_types)
|
||||
|
||||
def load_split_items(self, split_path: str) -> list[dict]:
|
||||
raw_items = super().load_split_items(split_path)
|
||||
source_path = next(
|
||||
(
|
||||
os.path.join(split_path, name)
|
||||
for name in sorted(os.listdir(split_path))
|
||||
if name.endswith(".json")
|
||||
),
|
||||
split_path,
|
||||
)
|
||||
items: list[dict] = []
|
||||
for row_idx, item in enumerate(raw_items):
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
norm = _normalize_item(
|
||||
item,
|
||||
row_idx=row_idx,
|
||||
source_path=source_path,
|
||||
data_root=self.data_root,
|
||||
problem_version=self.problem_version,
|
||||
text_dominant_map=self._text_dominant_map,
|
||||
)
|
||||
if norm is not None:
|
||||
items.append(norm)
|
||||
if not items:
|
||||
raise ValueError(
|
||||
f"No valid MathVerse items loaded from {split_path} "
|
||||
f"for problem_version={self.problem_version!r}"
|
||||
)
|
||||
return items
|
||||
@@ -0,0 +1,180 @@
|
||||
"""MathVerse evaluation helpers."""
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import string
|
||||
|
||||
from skillopt.model import chat_with_deployment
|
||||
from skillopt.prompts import load_prompt
|
||||
|
||||
|
||||
_EVAL_MODE = "mathverse_choice_or_judge_v1"
|
||||
|
||||
|
||||
def normalize_text(text: str) -> str:
|
||||
text = str(text or "").strip().lower()
|
||||
text = text.replace("\\,", " ")
|
||||
text = text.replace("\\ ", " ")
|
||||
text = "".join(ch for ch in text if ch not in string.punctuation)
|
||||
return " ".join(text.split())
|
||||
|
||||
|
||||
def normalize_math_text(text: str) -> str:
|
||||
text = str(text or "").strip()
|
||||
text = text.replace("$", "")
|
||||
text = text.replace("\\mathrm", "")
|
||||
text = text.replace("{", "")
|
||||
text = text.replace("}", "")
|
||||
text = text.replace("~", " ")
|
||||
text = text.replace("\\,", " ")
|
||||
text = text.replace("\\ ", " ")
|
||||
return " ".join(text.split()).lower()
|
||||
|
||||
|
||||
def extract_answer(text: str | None) -> str:
|
||||
raw = str(text or "").strip()
|
||||
if not raw:
|
||||
return ""
|
||||
|
||||
tags = re.findall(r"<answer>\s*(.*?)\s*</answer>", raw, re.IGNORECASE | re.DOTALL)
|
||||
if tags:
|
||||
return tags[-1].strip()
|
||||
|
||||
boxed = re.findall(r"\\boxed\{(.*?)\}", raw, re.IGNORECASE | re.DOTALL)
|
||||
if boxed:
|
||||
return boxed[-1].strip()
|
||||
|
||||
lines = [ln.strip() for ln in raw.splitlines() if ln.strip()]
|
||||
if lines:
|
||||
return lines[-1]
|
||||
return raw
|
||||
|
||||
|
||||
def _judge_answer(
|
||||
*,
|
||||
item: dict,
|
||||
extracted_answer: str,
|
||||
judge_model: str,
|
||||
max_completion_tokens: int,
|
||||
retries: int,
|
||||
) -> dict:
|
||||
question = str(item.get("question_for_eval") or item.get("question") or "").strip()
|
||||
ground_truth = str(item.get("answer") or "").strip()
|
||||
raw, _ = chat_with_deployment(
|
||||
deployment=judge_model,
|
||||
system="You are a careful and strict mathematical answer evaluator.",
|
||||
user=load_prompt("judge", env="mathverse").format(
|
||||
question=question,
|
||||
groundtruth=ground_truth,
|
||||
modeloutput=extracted_answer,
|
||||
),
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
retries=retries,
|
||||
stage="mathverse_judge",
|
||||
)
|
||||
response = str(raw).strip().lower()
|
||||
if "true" in response:
|
||||
correct = True
|
||||
elif "false" in response:
|
||||
correct = False
|
||||
else:
|
||||
correct = False
|
||||
return {
|
||||
"raw": raw,
|
||||
"correct": correct,
|
||||
"reason": response,
|
||||
"matched_gold": ground_truth if correct else "",
|
||||
}
|
||||
|
||||
|
||||
def evaluate_item(
|
||||
*,
|
||||
item: dict,
|
||||
prediction_text: str,
|
||||
judge_model: str,
|
||||
max_completion_tokens: int = 256,
|
||||
retries: int = 5,
|
||||
) -> dict:
|
||||
extracted = extract_answer(prediction_text)
|
||||
|
||||
if item.get("is_choice"):
|
||||
predicted_label = str(extracted).strip().upper().rstrip(".):")
|
||||
correct_label = str(item["correct_choice"].get("label") or "").strip().upper()
|
||||
predicted_text = ""
|
||||
for choice in item.get("choices") or []:
|
||||
if str(choice.get("label") or "").strip().upper() == predicted_label:
|
||||
predicted_text = str(choice.get("text") or "").strip()
|
||||
break
|
||||
hard = 1.0 if predicted_label == correct_label else 0.0
|
||||
return {
|
||||
"evaluation_mode": _EVAL_MODE,
|
||||
"predicted_answer": extracted,
|
||||
"predicted_label": predicted_label,
|
||||
"predicted_text": predicted_text,
|
||||
"correct_label": correct_label,
|
||||
"correct_text": str(item["correct_choice"].get("text") or "").strip(),
|
||||
"em": hard,
|
||||
"f1": hard,
|
||||
"sub_em": hard,
|
||||
"judge_raw": "",
|
||||
"judge_reason": "exact_label_match" if hard else "label_mismatch",
|
||||
"matched_gold": correct_label if hard else "",
|
||||
}
|
||||
|
||||
gold_answer = str(item.get("answer") or "").strip()
|
||||
pred_norm = normalize_math_text(extracted)
|
||||
gold_norm = normalize_math_text(gold_answer)
|
||||
if pred_norm and gold_norm and pred_norm == gold_norm:
|
||||
return {
|
||||
"evaluation_mode": _EVAL_MODE,
|
||||
"predicted_answer": extracted,
|
||||
"em": 1.0,
|
||||
"f1": 1.0,
|
||||
"sub_em": 1.0,
|
||||
"judge_raw": "",
|
||||
"judge_reason": "normalized_exact_match",
|
||||
"matched_gold": gold_answer,
|
||||
"string_f1": 1.0,
|
||||
}
|
||||
|
||||
judge = _judge_answer(
|
||||
item=item,
|
||||
extracted_answer=extracted,
|
||||
judge_model=judge_model,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
retries=retries,
|
||||
)
|
||||
hard = 1.0 if judge["correct"] else 0.0
|
||||
pred_tokens = normalize_text(extracted).split()
|
||||
gold_tokens = normalize_text(gold_answer).split()
|
||||
overlap = 0
|
||||
gold_counts: dict[str, int] = {}
|
||||
for tok in gold_tokens:
|
||||
gold_counts[tok] = gold_counts.get(tok, 0) + 1
|
||||
for tok in pred_tokens:
|
||||
count = gold_counts.get(tok, 0)
|
||||
if count > 0:
|
||||
overlap += 1
|
||||
gold_counts[tok] = count - 1
|
||||
if pred_tokens and gold_tokens and overlap:
|
||||
precision = overlap / len(pred_tokens)
|
||||
recall = overlap / len(gold_tokens)
|
||||
string_f1 = 2 * precision * recall / (precision + recall)
|
||||
else:
|
||||
string_f1 = 0.0
|
||||
|
||||
return {
|
||||
"evaluation_mode": _EVAL_MODE,
|
||||
"predicted_answer": extracted,
|
||||
"em": hard,
|
||||
"f1": hard,
|
||||
"sub_em": hard,
|
||||
"judge_raw": judge["raw"],
|
||||
"judge_reason": judge["reason"],
|
||||
"matched_gold": judge["matched_gold"],
|
||||
"string_f1": string_f1,
|
||||
}
|
||||
|
||||
|
||||
def evaluation_mode() -> str:
|
||||
return _EVAL_MODE
|
||||
@@ -0,0 +1,37 @@
|
||||
You are an expert failure-analysis agent for visual mathematical reasoning problems.
|
||||
|
||||
You will be given MULTIPLE failed trajectories from a single minibatch and the current skill document.
|
||||
Each trajectory includes the student's response, the evaluation result, and sometimes a hidden reference
|
||||
containing the fuller Text Dominant version of the same problem.
|
||||
|
||||
Your job is to identify COMMON reasoning failures across the batch and propose concise skill edits.
|
||||
|
||||
## Failure Type Categories
|
||||
- **diagram_underuse**: the agent did not recover key constraints from the image
|
||||
- **constraint_drop**: the agent ignored a condition or relation that should guide the solution
|
||||
- **option_confusion**: the agent failed to discriminate between close answer choices
|
||||
- **format_miss**: the agent solved roughly correctly but returned the wrong final form, unit, or expression
|
||||
- **other**: none of the above
|
||||
|
||||
## Rules
|
||||
1. Focus on patterns that recur across the minibatch.
|
||||
2. Prefer edits that improve visual grounding and exact answer selection.
|
||||
3. Do not hardcode problem-specific formulas or answers.
|
||||
4. If hidden reference text is present, use it only to infer what information the student failed to recover from the Text Lite version.
|
||||
|
||||
Respond ONLY with a valid JSON object:
|
||||
{
|
||||
"batch_size": <number>,
|
||||
"failure_summary": [
|
||||
{"failure_type": "<type>", "count": <int>, "description": "<one-line>"}
|
||||
],
|
||||
"patch": {
|
||||
"reasoning": "<why these edits address the common failures>",
|
||||
"edits": [
|
||||
{"op": "append", "content": "<markdown>"},
|
||||
{"op": "insert_after", "target": "<heading/text>", "content": "<markdown>"},
|
||||
{"op": "replace", "target": "<old text>", "content": "<new text>"},
|
||||
{"op": "delete", "target": "<exact text to remove>"}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,26 @@
|
||||
You are an expert success-pattern analyst for visual mathematical reasoning problems.
|
||||
|
||||
You will be given MULTIPLE successful trajectories from a minibatch and the current skill document.
|
||||
Identify generalizable behavior patterns that genuinely help the agent recover the right constraints
|
||||
from the image and convert them into the exact final answer.
|
||||
|
||||
## Rules
|
||||
- Focus on broadly useful visual-math reasoning behaviors.
|
||||
- Prefer patterns about reading decisive diagram cues, checking hidden assumptions, and matching the final answer format exactly.
|
||||
- Do not add benchmark-specific facts or formulas.
|
||||
- "edits" may be empty if the skill already captures the useful patterns.
|
||||
|
||||
Respond ONLY with a valid JSON object:
|
||||
{
|
||||
"batch_size": <number>,
|
||||
"success_patterns": ["<pattern 1>", "<pattern 2>"],
|
||||
"patch": {
|
||||
"reasoning": "<why these patterns matter>",
|
||||
"edits": [
|
||||
{"op": "append", "content": "<markdown>"},
|
||||
{"op": "insert_after", "target": "<heading/text>", "content": "<markdown>"},
|
||||
{"op": "replace", "target": "<old text>", "content": "<new text>"},
|
||||
{"op": "delete", "target": "<exact text to remove>"}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
You are an expert diagnostic-probe designer for visual mathematical reasoning tasks.
|
||||
|
||||
You will be shown representative trajectories, the current student skill, and the student's original prompt context.
|
||||
Some trajectories may also include a hidden reference containing the fuller Text Dominant wording of the same problem.
|
||||
Design one SMALL diagnostic instruction that exposes the student's intermediate judgment without materially changing the original scaffold.
|
||||
|
||||
## Hard Constraints
|
||||
1. Do NOT substantially change the original scaffold.
|
||||
2. Do NOT prescribe a new long multi-step solving procedure.
|
||||
3. Do NOT ask for a full proof or full chain-of-thought.
|
||||
4. Ask only for a short readout of the signals already behind the student's current answer.
|
||||
5. Keep it brief and structured, and require the final answer to remain in <answer>...</answer>.
|
||||
6. If hidden reference text is present, use it only to target what visual or textual constraint the student likely missed.
|
||||
|
||||
## Good Probe Targets
|
||||
- decisive diagram cue
|
||||
- top candidate and runner-up
|
||||
- missing relation or quantity
|
||||
- why a near-miss option was rejected
|
||||
|
||||
Respond ONLY with a valid JSON object:
|
||||
{
|
||||
"reasoning": "<why this probe is informative>",
|
||||
"probe_instruction": "<the exact instruction text to append to the student prompt>"
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
You are a careful and strict evaluator for visual math problems.
|
||||
|
||||
You will be given:
|
||||
1. The original question
|
||||
2. The ground-truth answer
|
||||
3. A model output
|
||||
|
||||
Decide whether the model output is mathematically equivalent to the ground-truth answer.
|
||||
|
||||
Rules:
|
||||
- Ignore harmless formatting differences.
|
||||
- Accept mathematically equivalent expressions, equations, and values.
|
||||
- Reject answers that are numerically wrong, symbolically different in meaning, missing required units when the unit changes meaning, or correspond to a different choice.
|
||||
- Do not reward partially correct reasoning if the final answer is wrong.
|
||||
|
||||
Return only:
|
||||
True
|
||||
|
||||
or
|
||||
|
||||
False
|
||||
|
||||
Question: {question}
|
||||
Ground Truth Answer: {groundtruth}
|
||||
Model Output: {modeloutput}
|
||||
@@ -0,0 +1,11 @@
|
||||
You are an expert visual mathematical reasoning agent.
|
||||
|
||||
{skill_section}## Task Format
|
||||
You will receive one math problem with an image or diagram.
|
||||
Use the visible diagram as evidence, not just the text.
|
||||
If some information is abbreviated in the text, recover it from the image before answering.
|
||||
|
||||
## Answer Format
|
||||
Think step by step, then provide your final answer inside <answer>...</answer>.
|
||||
- For multiple-choice questions, output only the single option label, such as <answer>B</answer>.
|
||||
- For free-form questions, output only the final mathematical answer, such as <answer>14</answer>.
|
||||
@@ -0,0 +1,4 @@
|
||||
"""MathVerse Reflect stage.
|
||||
|
||||
Prompts are loaded from .md files by the base adapter.
|
||||
"""
|
||||
@@ -0,0 +1,415 @@
|
||||
"""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 skillopt.envs.mathverse.evaluator import evaluate_item, evaluation_mode, extract_answer
|
||||
from skillopt.model import chat_student_messages, get_student_backend, is_student_exec_backend
|
||||
from skillopt.model.codex_harness import prepare_workspace, render_skill_md, run_student_exec
|
||||
from skillopt.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 `skillopt-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 skillopt.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
|
||||
@@ -0,0 +1,15 @@
|
||||
# MathVerse Visual Math Heuristics
|
||||
|
||||
## Diagram First
|
||||
- Read the diagram before locking onto an equation or option.
|
||||
- Recover missing labels, lengths, angles, axes, or object relations from the image when the text is abbreviated.
|
||||
- If the text seems underspecified, assume the image may contain the decisive constraint.
|
||||
|
||||
## Constraint Tracking
|
||||
- Write down the few constraints that actually determine the answer instead of solving from vague intuition.
|
||||
- Prefer geometric or functional relations that are directly supported by the figure.
|
||||
- For multiple-choice questions, compare the final candidate against every option exactly.
|
||||
|
||||
## Final Answer
|
||||
- Use the image and the text consistently.
|
||||
- Return only the final answer inside <answer>...</answer>.
|
||||
Reference in New Issue
Block a user