Copertina

Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Yifan, Shi, Jingze, Wu, Bingheng, Zhang, Jiayi, Lin, Xiaotian, Tang, Nan, Luo, Yuyu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
di: Wu, Bingheng, et al.
Pubblicazione: (2025)

Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture
di: Shi, Jingze, et al.
Pubblicazione: (2024)

Trainable Dynamic Mask Sparse Attention
di: Shi, Jingze, et al.
Pubblicazione: (2025)

Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasks
di: Shi, Jingze, et al.
Pubblicazione: (2024)

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
di: Liang, Zhuowen, et al.
Pubblicazione: (2026)

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale
di: Shi, Jingze, et al.
Pubblicazione: (2026)

OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresser
di: Shi, Jingze, et al.
Pubblicazione: (2024)

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
di: Yang, Zhicheng, et al.
Pubblicazione: (2026)

RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
di: Fernandez, Nigel, et al.
Pubblicazione: (2025)

Concise Reasoning in the Lens of Lagrangian Optimization
di: Gao, Chengqian, et al.
Pubblicazione: (2025)

Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
di: Zhao, Bo, et al.
Pubblicazione: (2025)

AskChart: Universal Chart Understanding through Textual Enhancement
di: Yang, Xudong, et al.
Pubblicazione: (2024)

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning
di: Wang, Xukai, et al.
Pubblicazione: (2025)

Fine-Grained Knowledge Structuring and Retrieval for Visual Question Answering
di: Zhang, Zhengxuan, et al.
Pubblicazione: (2025)

ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
di: Li, Changyi, et al.
Pubblicazione: (2025)

ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation
di: Tang, Siao, et al.
Pubblicazione: (2025)

nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning
di: Luo, Tianqi, et al.
Pubblicazione: (2025)

DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering
di: Lin, Teng, et al.
Pubblicazione: (2026)

HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization
di: Huang, Chengyu, et al.
Pubblicazione: (2025)

LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
di: Lin, Xiaotian, et al.
Pubblicazione: (2025)

ContraPrompt: Contrastive Prompt Optimization via Dyadic Reasoning Trace Analysis
di: Rishav, Rishav, et al.
Pubblicazione: (2026)

G-SAP: Graph-based Structure-Aware Prompt Learning over Heterogeneous Knowledge for Commonsense Reasoning
di: Dai, Ruiting, et al.
Pubblicazione: (2024)

Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
di: Qu, Yun, et al.
Pubblicazione: (2025)

Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning
di: Wu, Siyu, et al.
Pubblicazione: (2026)

The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
di: Rezazadeh, Navid, et al.
Pubblicazione: (2026)

ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering
di: Wu, Yifan, et al.
Pubblicazione: (2024)

EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing
di: Zhu, Yizhang, et al.
Pubblicazione: (2025)

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
di: Shen, Yi, et al.
Pubblicazione: (2025)

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models
di: Phan, Hoang, et al.
Pubblicazione: (2025)

Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
di: Liu, Jinkun, et al.
Pubblicazione: (2026)

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

Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
di: Hong, Bin, et al.
Pubblicazione: (2025)

Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
di: Li, Yawei, et al.
Pubblicazione: (2026)

Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost
di: Nayab, Sania, et al.
Pubblicazione: (2024)

Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning
di: Rakotonirina, Nathanaël Carraz, et al.
Pubblicazione: (2026)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
di: Didolkar, Aniket, et al.
Pubblicazione: (2025)

Concise and Organized Perception Facilitates Reasoning in Large Language Models
di: Liu, Junjie, et al.
Pubblicazione: (2023)

InfoPO: Information-Driven Policy Optimization for User-Centric Agents
di: Kong, Fanqi, et al.
Pubblicazione: (2026)

Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training
di: Wang, Chen, et al.
Pubblicazione: (2026)

Self-Supervised Prompt Optimization
di: Xiang, Jinyu, et al.
Pubblicazione: (2025)