Image de couverture de livre

Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Yiming, Shi, Zhenbo, Gao, Shuzheng, Gao, Cuiyun, Han, Peiyi, Liu, Chuanyi
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Emerging Technologies Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
par: Huang, Yiming, et autres
Publié: (2026)

Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization
par: Esencan, Mert, et autres
Publié: (2024)

Large Language models for Time Series Analysis: Techniques, Applications, and Challenges
par: Shi, Feifei, et autres
Publié: (2025)

InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior
par: Wang, Huisheng, et autres
Publié: (2025)

AgriLLM: Harnessing Transformers for Farmer Queries
par: Didwania, Krish, et autres
Publié: (2024)

TraceLLM: Security Diagnosis Through Traces and Smart Contracts in Ethereum
par: Wang, Shuzheng, et autres
Publié: (2025)

Bentō: Optimizing Persistent Memory Programs
par: Amaro, Sebastião, et autres
Publié: (2026)

Machine Translation with Large Language Models: Decoder Only vs. Encoder-Decoder
par: M., Abhinav P., et autres
Publié: (2024)

Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
par: Sadhu, Saisab, et autres
Publié: (2026)

When to Reason: Semantic Router for vLLM
par: Wang, Chen, et autres
Publié: (2025)

G-Zero: Self-Play for Open-Ended Generation from Zero Data
par: Huang, Chengsong, et autres
Publié: (2026)

Learning Personalized Utility Functions for Drivers in Ride-hailing Systems Using Ensemble Hypernetworks
par: Mai, Weiming, et autres
Publié: (2025)

Beyond the Mean: Modelling Annotation Distributions in Continuous Affect Prediction
par: Pinitas, Kosmas, et autres
Publié: (2026)

World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications
par: Zidan, Arif Hassan, et autres
Publié: (2026)

MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocation
par: Zhang, XiaoJie, et autres
Publié: (2026)

Machine Intelligence on Wireless Edge Networks
par: Vadlamani, Sri Krishna, et autres
Publié: (2025)

Effects of Prompt Length on Domain-specific Tasks for Large Language Models
par: Liu, Qibang, et autres
Publié: (2025)

A Dual Power Grid Cascading Failure Model for the Vulnerability Analysis
par: Zhou, Tianxin, et autres
Publié: (2024)

Adaptive Semantic Token Communication for Transformer-based Edge Inference
par: Devoto, Alessio, et autres
Publié: (2025)

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems
par: Moia, Vitor Hugo Galhardo, et autres
Publié: (2025)

Effect of Selection Format on LLM Performance
par: Han, Yuchen, et autres
Publié: (2025)

Robust Reasoning and Learning with Brain-Inspired Representations under Hardware-Induced Nonlinearities
par: Chung, William Youngwoo, et autres
Publié: (2026)

On Optimizing Hyperparameters for Quantum Neural Networks
par: Herbst, Sabrina, et autres
Publié: (2024)

Scalable Thermodynamic Second-order Optimization
par: Donatella, Kaelan, et autres
Publié: (2025)

Pruning for Improved ADC Efficiency in Crossbar-based Analog In-memory Accelerators
par: Ibrayev, Timur, et autres
Publié: (2024)

AutoGMap: Learning to Map Large-scale Sparse Graphs on Memristive Crossbars
par: Lyu, Bo, et autres
Publié: (2021)

Improving Performance Prediction of Electrolyte Formulations with Transformer-based Molecular Representation Model
par: Priyadarsini, Indra, et autres
Publié: (2024)

Trustworthy Tree-based Machine Learning by $MoS_2$ Flash-based Analog CAM with Inherent Soft Boundaries
par: Wen, Bo, et autres
Publié: (2025)

Unleashing the Expressive Power of Pulse-Based Quantum Neural Networks
par: Tao, Han-Xiao, et autres
Publié: (2024)

SAIL: Scene-aware Adaptive Iterative Learning for Long-Tail Trajectory Prediction in Autonomous Vehicles
par: Rao, Bin, et autres
Publié: (2026)

Struggling or Thriving With Technology at Work: A Mixed‐Method Analysis of Personal and Organizational ICT Resources
par: Rita Jakstiene, et autres
Publié: (2025)

NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs
par: Qin, Ruiyang, et autres
Publié: (2024)

Can Large Language Models Act as Symbolic Reasoners?
par: Sullivan, Rob, et autres
Publié: (2024)

Self-Adaptive Ising Machines for Constrained Optimization
par: Delacour, Corentin
Publié: (2025)

Generation of Optimized Solidity Code for Machine Learning Models using LLMs
par: Sham, Nikumbh Sarthak, et autres
Publié: (2025)

LLM-Aided Customizable Profiling of Code Data Based On Programming Language Concepts
par: Thorat, Pankaj, et autres
Publié: (2025)

Affordable Precision Agriculture: A Deployment-Oriented Review of Low-Cost, Low-Power Edge AI and TinyML for Resource-Constrained Farming Systems
par: Samanta, Riya, et autres
Publié: (2026)

Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer
par: Pelke, Rebecca, et autres
Publié: (2025)

A Hybrid Tucker-LSTM Tensor Network Model for SOC Prediction in Electric Vehicles
par: Wang, Han, et autres
Publié: (2026)

Machine Learning-assisted High-speed Combinatorial Optimization with Ising Machines for Dynamically Changing Problems
par: Hamakawa, Yohei, et autres
Publié: (2025)