Cover Image

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Chenyu, Chai, Huacan, Chen, Wenteng, Guo, Zihan, Shan, Rong, Song, Yuanyi, Xu, Tianyi, Yang, Yingxuan, Yu, Aofan, Zhang, Weiming, Zheng, Congming, Zhu, Jiachen, Zheng, Zeyu, Zhang, Zhuosheng, Lou, Xingyu, Zhang, Changwang, Fu, Zhihui, Wang, Jun, Liu, Weiwen, Lin, Jianghao, Zhang, Weinan
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
by: Chai, Huacan, et al.
Published: (2026)

Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use Agents
by: Wu, Zheng, et al.
Published: (2025)

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
by: Yang, Yingxuan, et al.
Published: (2025)

Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning
by: Wu, Zheng, et al.
Published: (2026)

OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrieval
by: Wang, Teng, et al.
Published: (2026)

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
by: Wang, Jingxing, et al.
Published: (2026)

A Survey of AI Agent Protocols
by: Yang, Yingxuan, et al.
Published: (2025)

ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution
by: Wang, Jihong, et al.
Published: (2026)

Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
by: Zhu, Jiachen, et al.
Published: (2026)

Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation
by: Zhang, Weiming, et al.
Published: (2026)

PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval
by: Xu, Tianyi, et al.
Published: (2026)

Adaptive Milestone Reward for GUI Agents
by: Zheng, Congmin, et al.
Published: (2026)

DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval
by: Qi, Siyuan, et al.
Published: (2026)

VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
by: Wu, Zheng, et al.
Published: (2025)

ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks
by: Song, Yuanyi, et al.
Published: (2025)

Superplatforms Have to Attack AI Agents
by: Lin, Jianghao, et al.
Published: (2025)

PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
by: Chai, Huacan, et al.
Published: (2025)

ColorEcosystem: Powering Personalized, Standardized, and Trustworthy Agentic Service in massive-agent Ecosystem
by: Wu, Fangwen, et al.
Published: (2025)

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
by: Zheng, Congmin, et al.
Published: (2025)

Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
by: Shan, Rong, et al.
Published: (2026)

SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval
by: Cui, Zicai, et al.
Published: (2026)

Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering
by: Zhu, Jiachen, et al.
Published: (2026)

MuonRec: Shifting the Optimizer Paradigm Beyond Adam in Scalable Generative Recommendation
by: Shan, Rong, et al.
Published: (2026)

A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models
by: Zheng, Congmin, et al.
Published: (2025)

ColorAgent: Building A Robust, Personalized, and Interactive OS Agent
by: Li, Ning, et al.
Published: (2025)

Stop DDoS Attacking the Research Community with AI-Generated Survey Papers
by: Lin, Jianghao, et al.
Published: (2025)

Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
by: Zhu, Jiachen, et al.
Published: (2025)

MemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Models
by: Xi, Yunjia, et al.
Published: (2024)

Agent Exchange: Shaping the Future of AI Agent Economics
by: Yang, Yingxuan, et al.
Published: (2025)

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
by: Pan, Shuai, et al.
Published: (2026)

A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
by: Xi, Yunjia, et al.
Published: (2025)

Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
by: Zhu, Jiachen, et al.
Published: (2025)

SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
by: Guo, Zihan, et al.
Published: (2026)

CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models
by: Fu, Lingyue, et al.
Published: (2023)

A Survey on Diffusion Models for Recommender Systems
by: Lin, Jianghao, et al.
Published: (2024)

Harnessing Fourier Transform Filter and Prompt Learning for Few‐Shot Event Detection
by: Mianshen Xu, et al.
Published: (2026)

M-scan: A Multi-Scenario Causal-driven Adaptive Network for Recommendation
by: Zhu, Jiachen, et al.
Published: (2024)

AFSPP: Agent Framework for Shaping Preference and Personality with Large Language Models
by: He, Zihong, et al.
Published: (2024)

Play to Your Strengths: Collaborative Intelligence of Conventional Recommender Models and Large Language Models
by: Xi, Yunjia, et al.
Published: (2024)

Beyond Positive History: Re-ranking with List-level Hybrid Feedback
by: Weng, Muyan, et al.
Published: (2024)