thinkdial-reasoning-effort-control

name	thinkdial-reasoning-effort-control
title	ThinkDial: Controlling Reasoning Effort in Large Language Models
version	0.0.2
engine	skillxiv-v0.0.2-claude-opus-4.6
license	MIT
url	https://arxiv.org/abs/2508.18773
keywords	["reasoning-budget","token-compression","controllable-inference","budget-aware-training","reward-shaping"]
description	Control LLM reasoning effort through discrete modes (High/Medium/Low) using budget-aware supervised fine-tuning and adaptive reward shaping, enabling compression-performance tradeoffs.

ThinkDial: Controlling Reasoning Effort in LLMs

Core Concept

ThinkDial enables dynamic control over reasoning computation in LLMs through discrete modes: High (full capability), Medium (50% token reduction), and Low (75% token reduction). The approach combines budget-aware supervised fine-tuning (embedding budget constraints early) with two-phase reinforcement learning (offline stability + online refinement). This enables practical compression-performance tradeoffs comparable to proprietary systems while remaining open-source.

Architecture Overview

• Discrete Reasoning Modes: Three effort levels with clear token budgets
• Budget-Aware SFT: Fine-tuning with explicit budget constraints
• Two-Phase RL: Offline + online for stable training
• Adaptive Reward Shaping: Budget-dependent rewards
• Mode Switching: Runtime selection of reasoning effort

Implementation Steps

1. Define Reasoning Modes and Budgets

Create discrete effort levels:

from dataclasses import dataclass
from enum import Enum
from typing import Dict

class ReasoningMode(Enum):
    HIGH = "high"
    MEDIUM = "medium"
    LOW = "low"

@dataclass
class BudgetConfig:
    """Token budget for reasoning mode."""
    mode: ReasoningMode
    max_tokens: int
    thinking_proportion: float  # What fraction should be thinking vs answering
    description: str

class ThinkDialConfig:
    """Configuration for ThinkDial reasoning modes."""

    BUDGETS = {
        ReasoningMode.HIGH: BudgetConfig(
            mode=ReasoningMode.HIGH,
            max_tokens=1000,
            thinking_proportion=,
            description=
        ),
        ReasoningMode.MEDIUM: BudgetConfig(
            mode=ReasoningMode.MEDIUM,
            max_tokens=,  
            thinking_proportion=,
            description=
        ),
        ReasoningMode.LOW: BudgetConfig(
            mode=ReasoningMode.LOW,
            max_tokens=,  
            thinking_proportion=,
            description=
        )
    }


     () -> BudgetConfig:
         ThinkDialConfig.BUDGETS[mode]


     () -> :
        
        budget = ThinkDialConfig.get_budget(mode)