Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kutschka, Lorenz, Geiger, Bernhard
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving Coherence and Persistence in Agentic AI for System Optimization
par: Karimi, Pantea, et autres
Publié: (2026)

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

GREEN: Generative Radiology Report Evaluation and Error Notation
par: Ostmeier, Sophie, et autres
Publié: (2024)

PAME-AI: Patient Messaging Creation and Optimization using Agentic AI
par: Luo, Junjie, et autres
Publié: (2025)

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics
par: Zur, Amir, et autres
Publié: (2025)

Towards the AI Historian: Agentic Information Extraction from Primary Sources
par: Hufe, Lorenz, et autres
Publié: (2026)

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
par: Wang, Dixuan, et autres
Publié: (2024)

Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens
par: Zhang, Meicong, et autres
Publié: (2025)

Semantic Invariance in Agentic AI
par: de Zarzà, I., et autres
Publié: (2026)

SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool Use
par: Jeon, Changhyun, et autres
Publié: (2025)

Tokenization Matters: Improving Zero-Shot NER for Indic Languages
par: Pattnayak, Priyaranjan, et autres
Publié: (2025)

HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization
par: Chen, Hongzheng, et autres
Publié: (2025)

MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use
par: Lei, Fei, et autres
Publié: (2025)

Classification of Human- and AI-Generated Texts for English, French, German, and Spanish
par: Schaaff, Kristina, et autres
Publié: (2023)

Token-level Direct Preference Optimization
par: Zeng, Yongcheng, et autres
Publié: (2024)

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

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
par: Nguyen, Truong, et autres
Publié: (2026)

ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
par: Zhang, Yifei, et autres
Publié: (2026)

AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
par: Yuan, Jiaqi, et autres
Publié: (2026)

The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models
par: Sun, Bohang, et autres
Publié: (2026)

DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
par: Zhang, Yinger, et autres
Publié: (2026)

MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation
par: Han, Taolin, et autres
Publié: (2026)

AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
par: Qi, Yunjia, et autres
Publié: (2025)

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

Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI
par: Sarin, Samarth, et autres
Publié: (2025)

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
par: Jiang, Pengcheng, et autres
Publié: (2025)

Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
par: Ovalle, Anaelia, et autres
Publié: (2023)

CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution
par: Zehle, Tom
Publié: (2026)

Understanding and Optimizing Agentic Workflows via Shapley value
par: Yang, Yingxuan, et autres
Publié: (2025)

CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning
par: Lu, Zhiyuan, et autres
Publié: (2026)

SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding
par: Hou, Shuyang, et autres
Publié: (2026)

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
par: Kong, Yaxuan, et autres
Publié: (2026)

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
par: Lin, Zicheng, et autres
Publié: (2024)

APRES: An Agentic Paper Revision and Evaluation System
par: Zhao, Bingchen, et autres
Publié: (2026)

Semantic XPath: Structured Agentic Memory Access for Conversational AI
par: Liu, Yifan Simon, et autres
Publié: (2026)

An Agentic AI Framework for Training General Practitioner Student Skills
par: De Marez, Victor, et autres
Publié: (2025)

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

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
par: Ding, Deming, et autres
Publié: (2026)

Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions
par: Lee, Yu-Ang, et autres
Publié: (2025)

Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI
par: Giusti, Lorenzo, et autres
Publié: (2025)