Image de couverture de livre

ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hamri, May, Talgam-Cohen, Inbal
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contracts
par: Ivanov, Dima, et autres
Publié: (2024)

Incentivizing Quality Text Generation via Statistical Contracts
par: Saig, Eden, et autres
Publié: (2024)

Statistically Truthful Auctions via Acceptance Rule
par: Lotan, Roy Maor, et autres
Publié: (2024)

Adaptive Contracts for Cost-Effective AI Delegation
par: Saig, Eden, et autres
Publié: (2026)

Adaptive Budget Allocation in LLM-Augmented Surveys
par: Ye, Zikun, et autres
Publié: (2026)

Stochastic Knapsack: Semi-Adaptivity Gaps and Improved Approximation
par: Barak, Zohar, et autres
Publié: (2026)

Online Resource Allocation with Average Budget Constraints
par: Ao, Ruicheng, et autres
Publié: (2024)

Efficient Budget Allocation for Large-Scale LLM-Enabled Virtual Screening
par: Li, Zaile, et autres
Publié: (2024)

How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
par: Feldman, Shai, et autres
Publié: (2026)

DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs
par: Song, Mingxuan, et autres
Publié: (2026)

Multi-Task Combinatorial Bandits for Budget Allocation
par: Ge, Lin, et autres
Publié: (2024)

Contracting with a Learning Agent
par: Guruganesh, Guru, et autres
Publié: (2024)

Local LLM Ensembles for Zero-shot Portuguese Named Entity Recognition
par: Sarcinelli, João Lucas Luz Lima, et autres
Publié: (2025)

Online Contract Design
par: Lavi, Elad, et autres
Publié: (2026)

Welfare and Beyond in Multi-Agent Contracts
par: Aharoni, Gil, et autres
Publié: (2025)

Dynamic Rental Games with Stagewise Individual Rationality
par: Berzack, Batya, et autres
Publié: (2025)

MAC Advice for Facility Location Mechanism Design
par: Barak, Zohar, et autres
Publié: (2024)

Algorithmic Contract Theory: A Survey
par: Duetting, Paul, et autres
Publié: (2024)

Budget Allocation for Unknown Value Functions in a Lipschitz Space
par: Bateni, MohammadHossein, et autres
Publié: (2025)

LLM-as-Judge on a Budget
par: Saha, Aadirupa, et autres
Publié: (2026)

Optimal Perturbation Budget Allocation for Data Poisoning in Offline Reinforcement Learning
par: Qiu, Junnan, et autres
Publié: (2025)

Zero-shot Forecasting by Simulation Alone
par: Oreshkin, Boris N., et autres
Publié: (2026)

TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation
par: Malettira, Prajna G., et autres
Publié: (2026)

PRISM: Differentially Private Synthetic Data with Structure-Aware Budget Allocation for Prediction
par: Asiaee, Amir, et autres
Publié: (2026)

ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs
par: Li, Yuhan, et autres
Publié: (2024)

ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing
par: Cheng, Guanjie, et autres
Publié: (2025)

DCoM: Active Learning for All Learners
par: Mishal, Inbal, et autres
Publié: (2024)

InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers
par: Yehuda, Yakir, et autres
Publié: (2024)

Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression
par: Miao, Ruijie, et autres
Publié: (2026)

Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning
par: Schram, Viktoria, et autres
Publié: (2026)

Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits
par: Nguyen, Nicolas, et autres
Publié: (2024)

Online Budget Allocation with Censored Semi-Bandit Feedback
par: Bachoc, François, et autres
Publié: (2025)

Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs
par: Flemings, James, et autres
Publié: (2025)

Zero-shot and Few-shot Generation Strategies for Artificial Clinical Records
par: Frayling, Erlend, et autres
Publié: (2024)

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
par: Hu, Haoyu, et autres
Publié: (2026)

Budgeted Attention Allocation: Cost-Conditioned Compute Control for Efficient Transformers
par: Nidhi, Amrit
Publié: (2026)

Adaptive LLM Routing under Budget Constraints
par: Panda, Pranoy, et autres
Publié: (2025)

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation
par: Shen, Yiqun, et autres
Publié: (2025)

Zero-shot World Models via Search in Memory
par: Malato, Federico, et autres
Publié: (2025)

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
par: Wen, Hao, et autres
Publié: (2025)