# Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMs

arXiv: https://arxiv.org/abs/2604.19780 · HTML: https://mlsanity.com/paper/2604.19780/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 28 of its 29 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 28 of 28)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning](https://mlsanity.com/paper/2504.00891/) (2025)
- [SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents](https://mlsanity.com/paper/2305.13040/) (2023)
- [SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning](https://mlsanity.com/paper/2505.11274/) (2025)
- [Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies](https://mlsanity.com/paper/2406.06461/) (2024)
- [Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2410.19732/) (2024)
- [Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback](https://mlsanity.com/paper/2501.01377/) (2025)
- [Steering LLM Thinking with Budget Guidance](https://mlsanity.com/paper/2506.13752/) (2025)
- [Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models](https://mlsanity.com/paper/2505.16122/) (2025)
- [Entropy-based Exploration Conduction for Multi-step Reasoning](https://mlsanity.com/paper/2503.15848/) (2025)
- [Optimizing Anytime Reasoning via Budget Relative Policy Optimization](https://mlsanity.com/paper/2505.13438/) (2025)
- [GATEAU: Selecting Influential Samples for Long Context Alignment](https://mlsanity.com/paper/2410.15633/) (2024)
- [HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization](https://mlsanity.com/paper/2505.11225/) (2025)
- [A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks](https://mlsanity.com/paper/2510.05608/) (2025)
- [DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment](https://mlsanity.com/paper/2504.18576/) (2025)
- [Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts](https://mlsanity.com/paper/2510.21557/) (2025)
- [Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2601.19280/) (2026)
- [Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification](https://mlsanity.com/paper/2509.26614/) (2025)
- [U-ViLAR: Uncertainty-Aware Visual Localization for Autonomous Driving via Differentiable Association and Registration](https://mlsanity.com/paper/2507.04503/) (2025)
- [Auto-Landmark: Acoustic Landmark Dataset and Open-Source Toolkit for Landmark Extraction](https://mlsanity.com/paper/2409.07969/) (2024)
- [DramaBench: A Six-Dimensional Evaluation Framework for Drama Script Continuation](https://mlsanity.com/paper/2512.19012/) (2025)

## Abstract (arXiv)

Scaling test-time compute via extended reasoning has become a key paradigm for improving the capabilities of large language models (LLMs). However, existing approaches optimize reasoning under fixed or uniformly sampled token budgets, ignoring the fundamental mismatch between problem difficulty and allocated compute. This leads to overthinking on easy problems and underthinking on hard ones, resulting in suboptimal token efficiency across diverse reasoning scenarios. In this paper, we propose Budget-Adaptive Curriculum Reasoning (BCAE), a unified framework that jointly optimizes reasoning quality and token efficiency through three synergistic components: (1) a budget-conditioned unified policy that embeds the token budget as a continuous conditioning signal, eliminating the need for decoupled thinking and summarization strategies; (2) a curriculum-aware budget scheduler that adaptively shifts the training budget distribution from easy to hard problems based on real-time learning progress; and (3) a truncation-aware dense reward mechanism that provides fine-grained credit assignment at intermediate reasoning steps via process-level verification. We further introduce Budget-Conditioned Advantage Estimation (BCAE), a novel variance reduction technique that conditions the advantage baseline on the sampled budget, yielding more stable policy gradients. Experiments on mathematical reasoning benchmarks (MATH, GSM8K, AIME, and Minerva Math) demonstrate that BACR consistently outperforms other strong baselines across all token budgets, achieving up to 8.3% accuracy improvement under tight budgets while reducing average token consumption by 34% compared to unconstrained reasoning.