Imagen de Portada

Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kutschka, Lorenz, Geiger, Bernhard
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improving Coherence and Persistence in Agentic AI for System Optimization
por: Karimi, Pantea, et al.
Publicado: (2026)

Token-Oriented Object Notation vs JSON: A Benchmark of Plain and Constrained Decoding Generation
por: Matveev, Ivan
Publicado: (2026)

GREEN: Generative Radiology Report Evaluation and Error Notation
por: Ostmeier, Sophie, et al.
Publicado: (2024)

PAME-AI: Patient Messaging Creation and Optimization using Agentic AI
por: Luo, Junjie, et al.
Publicado: (2025)

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics
por: Zur, Amir, et al.
Publicado: (2025)

Towards the AI Historian: Agentic Information Extraction from Primary Sources
por: Hufe, Lorenz, et al.
Publicado: (2026)

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
por: Wang, Dixuan, et al.
Publicado: (2024)

Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens
por: Zhang, Meicong, et al.
Publicado: (2025)

Semantic Invariance in Agentic AI
por: de Zarzà, I., et al.
Publicado: (2026)

SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool Use
por: Jeon, Changhyun, et al.
Publicado: (2025)

Tokenization Matters: Improving Zero-Shot NER for Indic Languages
por: Pattnayak, Priyaranjan, et al.
Publicado: (2025)

HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization
por: Chen, Hongzheng, et al.
Publicado: (2025)

MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use
por: Lei, Fei, et al.
Publicado: (2025)

Classification of Human- and AI-Generated Texts for English, French, German, and Spanish
por: Schaaff, Kristina, et al.
Publicado: (2023)

Token-level Direct Preference Optimization
por: Zeng, Yongcheng, et al.
Publicado: (2024)

Structured Context Engineering for File-Native Agentic Systems: Evaluating Schema Accuracy, Format Effectiveness, and Multi-File Navigation at Scale
por: McMillan, Damon
Publicado: (2026)

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
por: Nguyen, Truong, et al.
Publicado: (2026)

ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
por: Zhang, Yifei, et al.
Publicado: (2026)

AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
por: Yuan, Jiaqi, et al.
Publicado: (2026)

The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models
por: Sun, Bohang, et al.
Publicado: (2026)

DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
por: Zhang, Yinger, et al.
Publicado: (2026)

MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation
por: Han, Taolin, et al.
Publicado: (2026)

AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
por: Qi, Yunjia, et al.
Publicado: (2025)

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems
por: Shukla, Manish
Publicado: (2025)

Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI
por: Sarin, Samarth, et al.
Publicado: (2025)

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
por: Jiang, Pengcheng, et al.
Publicado: (2025)

Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
por: Ovalle, Anaelia, et al.
Publicado: (2023)

CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution
por: Zehle, Tom
Publicado: (2026)

Understanding and Optimizing Agentic Workflows via Shapley value
por: Yang, Yingxuan, et al.
Publicado: (2025)

CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning
por: Lu, Zhiyuan, et al.
Publicado: (2026)

SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding
por: Hou, Shuyang, et al.
Publicado: (2026)

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
por: Kong, Yaxuan, et al.
Publicado: (2026)

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
por: Lin, Zicheng, et al.
Publicado: (2024)

APRES: An Agentic Paper Revision and Evaluation System
por: Zhao, Bingchen, et al.
Publicado: (2026)

Semantic XPath: Structured Agentic Memory Access for Conversational AI
por: Liu, Yifan Simon, et al.
Publicado: (2026)

An Agentic AI Framework for Training General Practitioner Student Skills
por: De Marez, Victor, et al.
Publicado: (2025)

STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking
por: Chhetri, Tek Raj, et al.
Publicado: (2025)

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
por: Ding, Deming, et al.
Publicado: (2026)

Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions
por: Lee, Yu-Ang, et al.
Publicado: (2025)

Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI
por: Giusti, Lorenzo, et al.
Publicado: (2025)