End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Guanzhong, Yang, Shaoxiong, Li, Chao, Liu, Wei, Luan, Jian, Xu, Zenglin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation
by: Yan, Lingyong, et al.
Published: (2026)

TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors
by: Atad, Ido Andrew, et al.
Published: (2026)

End-to-End Evaluation and Governance of an EHR-Embedded AI Agent for Clinicians
by: Shah, Aaryan, et al.
Published: (2026)

Deep Dubbing: End-to-End Auto-Audiobook System with Text-to-Timbre and Context-Aware Instruct-TTS
by: Dai, Ziqi, et al.
Published: (2025)

LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English
by: Levine, Lauren, et al.
Published: (2026)

PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation
by: Wang, Yuchen, et al.
Published: (2026)

Agentic Automation of BT-RADS Scoring: End-to-End Multi-Agent System for Standardized Brain Tumor Follow-up Assessment
by: Jabal, Mohamed Sobhi, et al.
Published: (2026)

Toward Architecture-Aware Evaluation Metrics for LLM Agents
by: Souza, Débora, et al.
Published: (2026)

ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs
by: Cui, Jian, et al.
Published: (2026)

An End-to-End System for Culturally-Attuned Driving Feedback using a Dual-Component NLG Engine
by: Thompson, Iniakpokeikiye Peter, et al.
Published: (2025)

Test-Time Scaling of Reasoning Models for Machine Translation
by: Li, Zihao, et al.
Published: (2025)

EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents
by: Chen, Junting, et al.
Published: (2024)

Flippi: End To End GenAI Assistant for E-Commerce
by: Rajasekar, Anand A., et al.
Published: (2025)

An End-to-End Approach for Korean Wakeword Systems with Speaker Authentication
by: Seo, Geonwoo
Published: (2025)

Automatic End-to-End Data Integration using Large Language Models
by: Steiner, Aaron, et al.
Published: (2026)

SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning
by: Chang, Edward Y., et al.
Published: (2025)

Synergy: End-to-end Concept Model
by: Zheng, Keli, et al.
Published: (2025)

Improving Retrospective Language Agents via Joint Policy Gradient Optimization
by: Feng, Xueyang, et al.
Published: (2025)

CRISP: Persistent Concept Unlearning via Sparse Autoencoders
by: Ashuach, Tomer, et al.
Published: (2025)

ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning
by: Chang, Edward Y., et al.
Published: (2025)

Automatic Task Detection and Heterogeneous LLM Speculative Decoding
by: Ge, Danying, et al.
Published: (2025)

EVINCE: Optimizing Multi-LLM Dialogues Using Conditional Statistics and Information Theory
by: Chang, Edward Y.
Published: (2024)

Random Heterogeneous Neurochaos Learning Architecture for Data Classification
by: S, Remya Ajai A, et al.
Published: (2024)

FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
by: Yuan, Xin, et al.
Published: (2025)

Performance Evaluation of Sentiment Analysis on Text and Emoji Data Using End-to-End, Transfer Learning, Distributed and Explainable AI Models
by: Velampalli, Sirisha, et al.
Published: (2025)

Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias
by: Wu, Shuai, et al.
Published: (2026)

Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey
by: Vegner, Ivan, et al.
Published: (2025)

XPath Agent: An Efficient XPath Programming Agent Based on LLM for Web Crawler
by: Li, Yu, et al.
Published: (2024)

ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling
by: Han, William, et al.
Published: (2024)

Ada-MK: Adaptive MegaKernel Optimization via Automated DAG-based Search for LLM Inference
by: Dong, Wenxin, et al.
Published: (2026)

HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns
by: Wang, Xintao, et al.
Published: (2026)

PestMA: LLM-based Multi-Agent System for Informed Pest Management
by: Shi, Hongrui, et al.
Published: (2025)

Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development
by: Tran, Hung, et al.
Published: (2026)

Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
by: Wang, Zixu, et al.
Published: (2026)

SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM
by: Wang, Quandong, et al.
Published: (2024)

CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems
by: Sun, Kangkang, et al.
Published: (2026)

Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Design
by: Yao, Huaiyuan, et al.
Published: (2025)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
by: Peters, Sydney, et al.
Published: (2025)

Efficient Reasoning via Thought-Training and Thought-Free Inference
by: Wu, Canhui, et al.
Published: (2025)

Extracting Structured Insights from Financial News: An Augmented LLM Driven Approach
by: Dolphin, Rian, et al.
Published: (2024)