Cover Image

The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Weize, Yuan, Jiarui, Jin, Tailin, Ding, Ning, Chen, Huimin, Liu, Zhiyuan, Sun, Maosong
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization
by: Yuan, Jiarui, et al.
Published: (2026)

Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System
by: Chen, Weize, et al.
Published: (2024)

Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
by: Chen, Weize, et al.
Published: (2024)

PersLLM: A Personified Training Approach for Large Language Models
by: Zeng, Zheni, et al.
Published: (2024)

CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning
by: Li, Ran, et al.
Published: (2026)

From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones
by: Yuan, Lifan, et al.
Published: (2025)

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
by: Gao, Cheng, et al.
Published: (2025)

States Hidden in Hidden States: LLMs Emerge Discrete State Representations Implicitly
by: Chen, Junhao, et al.
Published: (2024)

Empowering Private Tutoring by Chaining Large Language Models
by: Chen, Yulin, et al.
Published: (2023)

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
by: Chen, Weize, et al.
Published: (2024)

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
by: Guo, Yiju, et al.
Published: (2024)

Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slip Scripts
by: Chen, Yingfa, et al.
Published: (2024)

Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning
by: Guo, Yiju, et al.
Published: (2025)

$\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens
by: Zhang, Xinrong, et al.
Published: (2024)

Mitigating Overthinking through Reasoning Shaping
by: Song, Feifan, et al.
Published: (2025)

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

Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
by: Li, Xin, et al.
Published: (2024)

Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models
by: Ding, Ning, et al.
Published: (2024)

KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs
by: Wu, Dingjun, et al.
Published: (2025)

AgentRM: Enhancing Agent Generalization with Reward Modeling
by: Xia, Yu, et al.
Published: (2025)

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

The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning
by: He, Bingxiang, et al.
Published: (2024)

Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
by: Ping, Bowen, et al.
Published: (2024)

Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
by: Han, Jinyi, et al.
Published: (2025)

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

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
by: He, Bingxiang, et al.
Published: (2025)

Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts
by: Wang, Xing, et al.
Published: (2025)

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
by: Wang, Hanqing, et al.
Published: (2024)

Iterative Experience Refinement of Software-Developing Agents
by: Qian, Chen, et al.
Published: (2024)

Advancing LLM Reasoning Generalists with Preference Trees
by: Yuan, Lifan, et al.
Published: (2024)

REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
by: Zhu, Yijie, et al.
Published: (2025)

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

ChatDev: Communicative Agents for Software Development
by: Qian, Chen, et al.
Published: (2023)

Experiential Co-Learning of Software-Developing Agents
by: Qian, Chen, et al.
Published: (2023)

VisRAG 2.0: Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation
by: Sun, Yubo, et al.
Published: (2025)

Stuffed Mamba: Oversized States Lead to the Inability to Forget
by: Chen, Yingfa, et al.
Published: (2024)

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

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

Process Reinforcement through Implicit Rewards
by: Cui, Ganqu, et al.
Published: (2025)

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