Copertina

Optimizing Token Consumption in LLMs: A Nano Surge Approach for Code Reasoning Efficiency

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hu, Junwei, Zheng, Weicheng, Liu, Yihan, Liu, Yan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

EffiReasonTrans: RL-Optimized Reasoning for Code Translation
di: Wang, Yanlin, et al.
Pubblicazione: (2025)

Evaluating LLMs Code Reasoning Under Real-World Context
di: Liu, Changshu
Pubblicazione: (2026)

Write Your Own CodeChecker: An Automated Test-Driven Checker Development Approach with LLMs
di: Liu, Jun, et al.
Pubblicazione: (2024)

When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention
di: Guo, Lianghong, et al.
Pubblicazione: (2024)

On Evaluating the Efficiency of Source Code Generated by LLMs
di: Niu, Changan, et al.
Pubblicazione: (2024)

Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand
di: Sun, Zhensu, et al.
Pubblicazione: (2025)

DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning
di: Wang, Yanlin, et al.
Pubblicazione: (2026)

CC2Vec: Combining Typed Tokens with Contrastive Learning for Effective Code Clone Detection
di: Dou, Shihan, et al.
Pubblicazione: (2024)

SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
di: Gao, Yudong, et al.
Pubblicazione: (2026)

Measuring Code Efficiency Optimization Capabilities with ACEOB
di: Pan, Yue, et al.
Pubblicazione: (2024)

STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis
di: Liu, Junwei, et al.
Pubblicazione: (2024)

CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning
di: Tang, Lingxiao, et al.
Pubblicazione: (2025)

UniCode: Augmenting Evaluation for Code Reasoning
di: Zheng, Xinyue, et al.
Pubblicazione: (2025)

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
di: Manh, Dung Nguyen, et al.
Pubblicazione: (2024)

A Benchmark for Evaluating Repository-Level Code Agents with Intermediate Reasoning on Feature Addition Task
di: Liu, Shuhan, et al.
Pubblicazione: (2026)

PEACE: Towards Efficient Project-Level Efficiency Optimization via Hybrid Code Editing
di: Ren, Xiaoxue, et al.
Pubblicazione: (2025)

Delving into Parameter-Efficient Fine-Tuning in Code Change Learning: An Empirical Study
di: Liu, Shuo, et al.
Pubblicazione: (2024)

Not All Tokens Matter: Data-Centric Optimization for Efficient Code Summarization
di: Afrin, Saima, et al.
Pubblicazione: (2026)

Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs
di: CodeArts Model Team, et al.
Pubblicazione: (2026)

CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks
di: Xie, Danning, et al.
Pubblicazione: (2025)

Prompt Learning for Multi-Label Code Smell Detection: A Promising Approach
di: Liu, Haiyang, et al.
Pubblicazione: (2024)

Evaluating the Energy-Efficiency of the Code Generated by LLMs
di: Islam, Md Arman, et al.
Pubblicazione: (2025)

LLMs are Bug Replicators: An Empirical Study on LLMs' Capability in Completing Bug-prone Code
di: Guo, Liwei, et al.
Pubblicazione: (2025)

Exploring the Capabilities of LLMs for Code Change Related Tasks
di: Fan, Lishui, et al.
Pubblicazione: (2024)

CodeGlance: Understanding Code Reasoning Challenges in LLMs through Multi-Dimensional Feature Analysis
di: Wang, Yunkun, et al.
Pubblicazione: (2026)

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
di: Du, Mingzhe, et al.
Pubblicazione: (2025)

CREME: Robustness Enhancement of Code LLMs via Layer-Aware Model Editing
di: Liu, Shuhan, et al.
Pubblicazione: (2025)

A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models
di: Liu, Changshu, et al.
Pubblicazione: (2025)

CodeMapper: A Language-Agnostic Approach to Mapping Code Regions Across Commits
di: Hu, Huimin, et al.
Pubblicazione: (2025)

Doctor: Optimizing Container Rebuild Efficiency by Instruction Re-Orchestration
di: Zhu, Zhiling, et al.
Pubblicazione: (2025)

COFFE: A Code Efficiency Benchmark for Code Generation
di: Peng, Yun, et al.
Pubblicazione: (2025)

Towards Verified Code Reasoning by LLMs
di: Sistla, Meghana, et al.
Pubblicazione: (2025)

Evolving Triple Knowledge-Augmented LLMs for Code Translation in Repository Context
di: Ou, Guangsheng, et al.
Pubblicazione: (2025)

Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs
di: Wang, Shufan, et al.
Pubblicazione: (2025)

Defects4Log: Benchmarking LLMs for Logging Code Defect Detection and Reasoning
di: Wang, Xin, et al.
Pubblicazione: (2025)

EffiSkill: Agent Skill Based Automated Code Efficiency Optimization
di: Wang, Zimu, et al.
Pubblicazione: (2026)

Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
di: Wang, Chong, et al.
Pubblicazione: (2024)

Decoding Secret Memorization in Code LLMs Through Token-Level Characterization
di: Nie, Yuqing, et al.
Pubblicazione: (2024)

Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision
di: Lin, Hong Yi, et al.
Pubblicazione: (2026)

AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMs
di: Liu, Jinshi, et al.
Pubblicazione: (2026)