メニュー
Decompose complex queries into sub-questions and allocate computational budgets adaptively based on estimated difficulty, achieving 70% accuracy improvements and 39% token reduction without retraining.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/ADu2021/skillXiv --skill plan-budget-reasoningコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Convert arXiv papers into ready-to-use agent skills using category-aware extraction. First classifies the paper into one or more of 11 research categories, then applies a specialized extraction pipeline for each category — because different types of papers produce different types of usable knowledge. A single paper can yield multiple skills if it spans categories. Use this skill whenever the user wants to turn a paper into a skill, extract practical techniques from research, build a skill library from papers, convert arXiv papers into reusable agent instructions, or batch-process multiple papers into skills. Also trigger when someone asks about extracting actionable knowledge from papers, making research practical for LLM agents, or systematically converting academic contributions into structured agent capabilities.
Establish regret bounds for behavior cloning with discretized actions combining statistical error and quantization error terms. Prove smoothness requirements for safe quantizer design, show that learning-based quantizers fail these requirements, and propose model-based augmentation to reduce error dependence from H² to H.
Dynamically allocate LoRA ranks per-layer during fine-tuning instead of using fixed uniform ranks. Learn optimal rank for each layer and subject via variational framework with discretized exponential distribution, reducing memory footprint while maintaining fidelity and text-alignment.
SOC 職業分類に基づく
SKILL.md を表示中
| name | plan-budget-reasoning |
| title | Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning |
| version | 0.0.2 |
| engine | skillxiv-v0.0.2-claude-opus-4.6 |
| license | MIT |
| url | https://arxiv.org/abs/2505.16122 |
| keywords | ["test-time compute","reasoning","token allocation","efficiency","LLMs"] |
| description | Decompose complex queries into sub-questions and allocate computational budgets adaptively based on estimated difficulty, achieving 70% accuracy improvements and 39% token reduction without retraining. |
Plan and Budget addresses the "overthinking" problem in language model reasoning: models generate excessively verbose outputs using computational resources inefficiently. The framework decomposes complex queries into sub-questions with varying uncertainty levels, then allocates tokens adaptively to each sub-problem based on estimated difficulty.
Rather than applying uniform computation across all reasoning steps, the approach identifies which sub-questions require more reasoning effort and concentrates tokens there, while keeping straightforward sub-questions brief. This test-time strategy is model-agnostic and requires no retraining, achieving both higher accuracy and reduced token consumption.
The following steps outline how to implement adaptive budget allocation for reasoning:
from typing import List, Dict, Tuple
from dataclasses import dataclass
import torch
@dataclass
:
text:
estimated_difficulty:
allocated_tokens:
response: =
:
():
.model = decomposition_model
() -> []:
prompt =
response = .model.generate(prompt, max_tokens=)
sub_questions = ._parse_sub_questions(response)
sub_questions
() -> []:
lines = response.split()
sub_questions = []
line lines:
line = line.strip()
line (c.isdigit() c line[:]):
question = line.lstrip().strip()
question:
sub_questions.append(question)
sub_questions
:
():
.model = estimation_model
() -> :
prompt =
response = .model.generate(prompt, max_tokens=)
:
difficulty = (response.strip())
(, (, difficulty))
:
:
():
.base_budget = base_budget
() -> [SubQuestion]:
sub_questions:
[]
min_tokens =
total_difficulty = (sq.estimated_difficulty sq sub_questions)
total_difficulty == :
total_difficulty = (sub_questions)
sq sub_questions:
proportion = sq.estimated_difficulty / total_difficulty
allocated = (.base_budget * proportion)
sq.allocated_tokens = (min_tokens, allocated)
sub_questions
:
() -> :
accuracy_improvement = (optimized_accuracy - baseline_accuracy) / baseline_accuracy
token_reduction = - (optimized_tokens / baseline_tokens)
e3 = accuracy_improvement + token_reduction
e3
:
():
.decomposer = decomposer
.estimator = estimator
.allocator = allocator
.reasoner = reasoner_model
() -> :
sub_question_texts = .decomposer.decompose(query)
sub_questions = [SubQuestion(text=sq, estimated_difficulty=, allocated_tokens=)
sq sub_question_texts]
sq sub_questions:
sq.estimated_difficulty = .estimator.estimate(sq.text)
allocator = BudgetAllocator(total_budget)
sub_questions = allocator.allocate(sub_questions)
total_tokens_used =
sq sub_questions:
response = .reasoner.generate(sq.text, max_tokens=sq.allocated_tokens)
sq.response = response
total_tokens_used += (response.split())
final_answer = ._synthesize(query, sub_questions)
{
: query,
: sub_questions,
: final_answer,
: total_tokens_used,
: total_tokens_used / total_budget
}
() -> :
context = .join([ sq sub_questions])
prompt =
final_answer = .reasoner.generate(prompt, max_tokens=)
final_answer
Budget allocation strategies:
Difficulty estimation approaches:
When to use:
When NOT to use:
Common pitfalls:
Plan and Budget achieves up to 70% accuracy improvements and 39% token reduction without retraining. The framework enables smaller models (32B parameters) to match larger models' efficiency. Code is publicly available and the work was accepted to ICLR 2026.
Original paper: "Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning" (arxiv.org/abs/2505.16122)