Image de couverture de livre

VORTEX: Aligning Task Utility and Human Preferences through LLM-Guided Reward Shaping

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xiong, Guojun, Tambe, Milind
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Health Facility Location in Ethiopia: Leveraging LLMs to Integrate Expert Knowledge into Algorithmic Planning
par: Trabelsi, Yohai, et autres
Publié: (2026)

Embeddings for Preferences, Not Semantics
par: Blair, Carter, et autres
Publié: (2026)

Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
par: Kong, Lingkai, et autres
Publié: (2025)

Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents
par: Tec, Mauricio, et autres
Publié: (2025)

Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards
par: Verma, Shresth, et autres
Publié: (2024)

Reward Shaping for Inference-Time Alignment: A Stackelberg Game Perspective
par: Wang, Haichuan, et autres
Publié: (2026)

Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and Fairness
par: Parthasarathy, Ambreesh, et autres
Publié: (2025)

LLM-based Agent Simulation for Maternal Health Interventions: Uncertainty Estimation and Decision-focused Evaluation
par: Martinson, Sarah, et autres
Publié: (2025)

Optimizing Vital Sign Monitoring in Resource-Constrained Maternal Care: An RL-Based Restless Bandit Approach
par: Boehmer, Niclas, et autres
Publié: (2024)

Towards Foundation-model-based Multiagent System to Accelerate AI for Social Impact
par: Zhao, Yunfan, et autres
Publié: (2024)

Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous Agents
par: Gordon, Lucia, et autres
Publié: (2024)

What is the Right Notion of Distance between Predict-then-Optimize Tasks?
par: Rodriguez-Diaz, Paula, et autres
Publié: (2024)

LLM Active Alignment: A Nash Equilibrium Perspective
par: Wang, Tonghan, et autres
Publié: (2026)

Many Preferences, Few Policies: Towards Scalable Language Model Personalization
par: Kim, Cheol Woo, et autres
Publié: (2026)

Aligning Crowd Feedback via Distributional Preference Reward Modeling
par: Li, Dexun, et autres
Publié: (2024)

OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
par: Zaregarizi, Shadmehr, et autres
Publié: (2026)

Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize
par: Shah, Sanket, et autres
Publié: (2023)

Efficient Public Health Intervention Planning Using Decomposition-Based Decision-Focused Learning
par: Shah, Sanket, et autres
Publié: (2024)

From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge
par: Wu, Xiefeng
Publié: (2024)

Boosting LLM Reasoning via Human-Inspired Reward Shaping
par: Lin, Wenze, et autres
Publié: (2026)

On Sequential Fault-Intolerant Process Planning
par: Kaczmarczyk, Andrzej, et autres
Publié: (2025)

Fairness for Workers Who Pull the Arms: An Index Based Policy for Allocation of Restless Bandit Tasks
par: Biswas, Arpita, et autres
Publié: (2023)

Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective
par: Kim, Cheol Woo, et autres
Publié: (2026)

MAESTRO: Multi-Agent Environment Shaping through Task and Reward Optimization
par: Wu, Boyuan
Publié: (2025)

A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
par: Behari, Nikhil, et autres
Publié: (2024)

Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming
par: Bhambri, Siddhant, et autres
Publié: (2023)

Reinforcement learning with combinatorial actions for coupled restless bandits
par: Xu, Lily, et autres
Publié: (2025)

Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
par: Ai, Rui, et autres
Publié: (2025)

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
par: Wu, Keming, et autres
Publié: (2025)

LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots
par: Han, Dongge, et autres
Publié: (2024)

Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
par: Shankar, Shreya, et autres
Publié: (2024)

Learning to Align Human Code Preferences
par: Yin, Xin, et autres
Publié: (2025)

Online Allocation with Unknown Shared Supply
par: Neoh, Tzeh Yuan, et autres
Publié: (2026)

MTRec: Learning to Align with User Preferences via Mental Reward Models
par: Zhao, Mengchen, et autres
Publié: (2025)

Decisions and Deployment: The Five-Year SAHELI Project (2020-2025) on Restless Multi-Armed Bandits for Improving Maternal and Child Health
par: Verma, Shresth, et autres
Publié: (2026)

Reward-Guided Speculative Decoding for Efficient LLM Reasoning
par: Liao, Baohao, et autres
Publié: (2025)

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
par: Dong, Zibin, et autres
Publié: (2023)

Contrasting local and global modeling with machine learning and satellite data: A case study estimating tree canopy height in African savannas
par: Rolf, Esther, et autres
Publié: (2024)

Beyond Listenership: AI-Predicted Interventions Drive Improvements in Maternal Health Behaviours
par: Dasgupta, Arpan, et autres
Publié: (2025)

Capturing Individual Human Preferences with Reward Features
par: Barreto, André, et autres
Publié: (2025)