Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rahman, Amirul, Karim, Aisha, Nakamura, Kenji, Ng, Yi-Fan
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
por: Su, Jinyan, et al.
Publicado: (2025)

Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling
por: Jiang, Shuyang, et al.
Publicado: (2025)

OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
por: Aggarwal, Pranjal, et al.
Publicado: (2025)

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
por: Wang, Yue, et al.
Publicado: (2025)

Fault Diagnosis in Power Grids with Large Language Model
por: Jing, Liu, et al.
Publicado: (2024)

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
por: Chen, Xingyu, et al.
Publicado: (2024)

Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models
por: Srivastava, Saurabh, et al.
Publicado: (2025)

Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
por: Srivastava, Gaurav, et al.
Publicado: (2025)

SA-GCS: Semantic-Aware Gaussian Curriculum Scheduling for UAV Vision-Language Navigation
por: Cai, Hengxing, et al.
Publicado: (2025)

SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration
por: Zhang, Xichen, et al.
Publicado: (2025)

Mitigating Overthinking through Reasoning Shaping
por: Song, Feifan, et al.
Publicado: (2025)

AraHalluEval: A Fine-grained Hallucination Evaluation Framework for Arabic LLMs
por: Alansari, Aisha, et al.
Publicado: (2025)

Think, But Don't Overthink: Reproducing Recursive Language Models
por: Wang, Daren
Publicado: (2026)

LLMs Are Zero-Shot Context-Aware Simultaneous Translators
por: Koshkin, Roman, et al.
Publicado: (2024)

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
por: Pu, Xiao, et al.
Publicado: (2025)

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit
por: Yi, Biao, et al.
Publicado: (2025)

Do LLMs Really Need 10+ Thoughts for "Find the Time 1000 Days Later"? Towards Structural Understanding of LLM Overthinking
por: Zhang, Xinliang Frederick, et al.
Publicado: (2025)

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
por: Fan, Chenrui, et al.
Publicado: (2025)

The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
por: Chen, Weize, et al.
Publicado: (2025)

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
por: Sui, Yang, et al.
Publicado: (2025)

Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
por: Peng, Keqin, et al.
Publicado: (2025)

SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation
por: Yang, Zeyu, et al.
Publicado: (2025)

Position: Avoid Overstretching LLMs for every Enterprise Task
por: Singh, Kuldeep, et al.
Publicado: (2026)

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning
por: Li, Yangning, et al.
Publicado: (2025)

DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models
por: Yan, Kaiwen, et al.
Publicado: (2025)

Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
por: Bin, Yi, et al.
Publicado: (2025)

Overthinking Loops in Agents: A Structural Risk via MCP Tools
por: Lee, Yohan, et al.
Publicado: (2026)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
por: Wei, Zihao, et al.
Publicado: (2025)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
por: Hassid, Michael, et al.
Publicado: (2025)

Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis
por: Vamvourellis, Dimitris, et al.
Publicado: (2025)

MaLei at MultiClinSUM: Summarisation of Clinical Documents using Perspective-Aware Iterative Self-Prompting with LLMs
por: Ren, Libo, et al.
Publicado: (2025)

Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning
por: Nguyen, Manh, et al.
Publicado: (2026)

Budget-Aware Anytime Reasoning with LLM-Synthesized Preference Data
por: Zhang, Xuanming, et al.
Publicado: (2026)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
por: Huang, Yao, et al.
Publicado: (2025)

Let LRMs Break Free from Overthinking via Self-Braking Tuning
por: Zhao, Haoran, et al.
Publicado: (2025)

Budget-Aware Routing for Long Clinical Text
por: Qureshi, Khizar, et al.
Publicado: (2026)

AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
por: Huang, Shijue, et al.
Publicado: (2025)

LLMs on a Budget? Say HOLA
por: Siddiqui, Zohaib Hasan, et al.
Publicado: (2025)

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
por: Diao, Xingjian, et al.
Publicado: (2026)

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
por: Jedidi, Nour, et al.
Publicado: (2025)