Imagen de Portada

Latent Action Reparameterization for Efficient Agent Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Wenhao, Zeng, Qingwen, Chen, Qiyue, Guo, Zijie, Sun, Yu, Yang, Cheng, Ouyang, Siru, Gesi, Jiri, Wu, Fang, Zhang, Jiayi, Chen, Huaming, Liu, Bang, Tang, Xiangru, Wu, Chenglin
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

M-$LLM^3$REC: A Motivation-Aware User-Item Interaction Framework for Enhancing Recommendation Accuracy with LLMs
por: Chen, Lining, et al.
Publicado: (2025)

Beyond Self-learned Attention: Mitigating Attention Bias in Transformer-based Models Using Attention Guidance
por: Gesi, Jiri, et al.
Publicado: (2024)

MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
por: Tang, Xiangru, et al.
Publicado: (2025)

InfoPO: Information-Driven Policy Optimization for User-Centric Agents
por: Kong, Fanqi, et al.
Publicado: (2026)

Foe for Fraud: Transferable Adversarial Attacks in Credit Card Fraud Detection
por: Fok, Jan Lum, et al.
Publicado: (2025)

NSW-EPNews: A News-Augmented Benchmark for Electricity Price Forecasting with LLMs
por: Bi, Zhaoge, et al.
Publicado: (2025)

AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning
por: Zhang, Jiayi, et al.
Publicado: (2025)

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
por: Chen, Jiaju, et al.
Publicado: (2025)

Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations
por: Cheng, Pengzhou, et al.
Publicado: (2025)

Importance Weighted Variational Inference without the Reparameterization Trick
por: Daudel, Kamélia, et al.
Publicado: (2026)

ReCode: Unify Plan and Action for Universal Granularity Control
por: Yu, Zhaoyang, et al.
Publicado: (2025)

LocAgent: Graph-Guided LLM Agents for Code Localization
por: Chen, Zhaoling, et al.
Publicado: (2025)

Human-aligned AI Model Cards with Weighted Hierarchy Architecture
por: Yang, Pengyue, et al.
Publicado: (2025)

AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines
por: Wu, Yifan, et al.
Publicado: (2026)

KANDU-Net:A Dual-Channel U-Net with KAN for Medical Image Segmentation
por: Fang, Chenglin, et al.
Publicado: (2024)

Improving Context Fidelity via Native Retrieval-Augmented Reasoning
por: Wang, Suyuchen, et al.
Publicado: (2025)

TinyIO: Lightweight Reparameterized Inertial Odometry
por: Zhang, Shanshan, et al.
Publicado: (2025)

Scalable Environments Drive Generalizable Agents
por: Zhang, Jiayi, et al.
Publicado: (2026)

Towards Robustness Analysis of E-Commerce Ranking System
por: Wang, Ningfei, et al.
Publicado: (2024)

Performative Prediction with Bandit Feedback: Learning through Reparameterization
por: Chen, Yatong, et al.
Publicado: (2023)

ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning
por: Tang, Xiangru, et al.
Publicado: (2025)

DiLA: Disentangled Latent Action World Models
por: Zhang, Tianqiu, et al.
Publicado: (2026)

Decocted Experience Improves Test-Time Inference in LLM Agents
por: Shen, Maohao, et al.
Publicado: (2026)

AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
por: Ruan, Jianhao, et al.
Publicado: (2026)

LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?
por: Sun, Lu, et al.
Publicado: (2025)

Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices
por: Ye, Shengyuan, et al.
Publicado: (2025)

Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference
por: Liu, Yudong, et al.
Publicado: (2026)

Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization
por: Shi, Bo-Yun, et al.
Publicado: (2025)

Co-Evolution of Policy and Internal Reward for Language Agents
por: Wang, Xinyu, et al.
Publicado: (2026)

De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution
por: Li, Dongqing, et al.
Publicado: (2026)

RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance
por: Jin, Haolin, et al.
Publicado: (2024)

Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures
por: Lin, Wu, et al.
Publicado: (2019)

Engineering Carbon Credits Towards A Responsible FinTech Era: The Practices, Implications, and Future
por: Zeng, Qingwen, et al.
Publicado: (2024)

Neural BRDF Importance Sampling by Reparameterization
por: Wu, Liwen, et al.
Publicado: (2025)

Does the Order of Fine-tuning Matter and Why?
por: Chen, Qihong, et al.
Publicado: (2024)

RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization
por: Zhao, Mingshu, et al.
Publicado: (2024)

StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning
por: Zhang, Yanfei, et al.
Publicado: (2026)

Self-Supervised Prompt Optimization
por: Xiang, Jinyu, et al.
Publicado: (2025)

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
por: Ouyang, Siru, et al.
Publicado: (2025)

Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel
por: Chen, Ruihua, et al.
Publicado: (2026)