Large Language Model Agent: A Survey on Methodology, Applications and Challenges

27 Mar 2025 · Junyu Luo, Weizhi Zhang, Ye Yuan, Yusheng Zhao, Junwei Yang, Yiyang Gu, Bohan Wu, Binqi Chen, Ziyue Qiao, Qingqing Long, RongCheng Tu, Xiao Luo, Wei Ju, Zhiping Xiao, Yifan Wang, Meng Xiao, Chenwu Liu, Jingyang Yuan, Shichang Zhang, Yiqiao Jin, Fan Zhang, Xian Wu, Hanqing Zhao, DaCheng Tao, Philip S. Yu, Ming Zhang

The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence. This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy, linking architectural foundations, collaboration mechanisms, and evolutionary pathways. We unify fragmented research threads by revealing fundamental connections between agent design principles and their emergent behaviors in complex environments. Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time, while also addressing evaluation methodologies, tool applications, practical challenges, and diverse application domains. By surveying the latest developments in this rapidly evolving field, we offer researchers a structured taxonomy for understanding LLM agents and identify promising directions for future research. The collection is available at https://github.com/luo-junyu/Awesome-Agent-Papers.

Paper: https://arxiv.org/pdf/2503.21460v1.pdf

Code: https://github.com/luo-junyu/awesome-agent-papers

https://t.iss.one/DataScienceT ✉️

Crystal Generation with Space Group Informed Transformer

🖥 Github: https://github.com/deepmodeling/crystalformer

📕 Paper: https://arxiv.org/abs/2504.02367v1

🔗 Dataset: https://paperswithcode.com/dataset/alex-20

CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models

28 Mar 2025 · Zhihang Lin, Mingbao Lin, Yuan Xie, Rongrong Ji

This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models based on Group Relative Policy Optimization (GRPO). GRPO, while effective, incurs high training costs due to the need for sampling multiple completions for each question. Our experiment and theoretical analysis reveals that the number of completions impacts model accuracy yet increases training time multiplicatively, and not all completions contribute equally to policy training -- their contribution depends on their relative advantage. To address these issues, we propose CPPO, which prunes completions with low absolute advantages, significantly reducing the number needed for gradient calculation and updates. Additionally, we introduce a dynamic completion allocation strategy to maximize GPU utilization by incorporating additional questions, further enhancing training efficiency. Experimental results demonstrate that CPPO achieves up to
speedup on GSM8K and on Math while preserving or even enhancing the accuracy compared to the original GRPO. We release our code at https://github.com/lzhxmu/CPPO.

Paper: https://arxiv.org/pdf/2503.22342v1.pdf

Code: https://github.com/lzhxmu/cppo

Datasets: GSM8K - MATH

https://t.iss.one/DataScienceT ⭐

🌳 Compose Anything is Out! 🌳
#SkyworkAI unveils #SkyReelsA2 — a controllable video generation framework that can assemble arbitrary visual elements (e.g., characters, objects, backgrounds) into fully synthesized videos from text prompts.
Code, models, and evaluation benchmark are all released!
🔗 Resources:
Review: https://t.ly/MEjzL
Paper: https://arxiv.org/pdf/2504.02436
Project: https://skyworkai.github.io/skyreels-a2.github.io/
Repo: https://github.com/SkyworkAI/SkyReels-A2
🤗 Models: https://huggingface.co/Skywork/SkyReels-A2

#AI #VideoGeneration #Multimodal #GenerativeAI #SkyReels #OpenSource

https://t.iss.one/DataScienceT ✅

This channels is for Programmers, Coders, Software Engineers.

0️⃣ Python
1️⃣ Data Science
2️⃣ Machine Learning
3️⃣ Data Visualization
4️⃣ Artificial Intelligence
5️⃣ Data Analysis
6️⃣ Statistics
7️⃣ Deep Learning
8️⃣ programming Languages

✅ https://t.iss.one/addlist/8_rRW2scgfRhOTc0

✅ https://t.iss.one/Codeprogrammer

🐈 TTT Long Video Generation 🐈

👉 A novel architecture for video generation, adapting the #CogVideoX 5B model by incorporating #TestTimeTraining (TTT) layers.
Adding TTT layers into a pre-trained Transformer enables generating a one-minute clip from text storyboards.
Videos, code & annotations released 💙

🔗 Review: https://t.ly/mhlTN
📄 Paper: arxiv.org/pdf/2504.05298
🌐 Project: test-time-training.github.io/video-dit
💻 Repo: github.com/test-time-training/ttt-video-dit

#AI #VideoGeneration #MachineLearning #DeepLearning #Transformers #TTT #GenerativeAI

⭐️ BEST DATA SCIENCE CHANNELS ON TELEGRAM ⭐️

🔥 #YOLOv12 is out – new SOTA! ⚡️

👉 YOLOv12 is a novel attention-centric YOLO framework that matches the speed of previous CNN-based versions while harnessing the performance benefits of attention mechanisms.

💙 Source Code & Demo released:
▶️ Review: https://t.ly/jj1oR
▶️ Paper: arXiv
👉 Repo: GitHub
🤗 Demo: https://t.ly/w5rno

#AI #DeepLearning #ComputerVision #YOLO #AttentionMechanism #OpenSource

Cheatsheet Machine Learning Algorithms

⚡️ BEST DATA SCIENCE CHANNELS ON TELEGRAM 🌟

📚 Become a professional data scientist with these 17 resources!



1️⃣ Python libraries for machine learning

◀️ Introducing the best Python tools and packages for building ML models.

➖➖➖

2️⃣ Deep Learning Interactive Book

◀️ Learn deep learning concepts by combining text, math, code, and images.

➖➖➖

3️⃣ Anthology of Data Science Learning Resources

◀️ The best courses, books, and tools for learning data science.

➖➖➖

4️⃣ Implementing algorithms from scratch

◀️ Coding popular ML algorithms from scratch

➖➖➖

5️⃣ Machine Learning Interview Guide

◀️ Fully prepared for job interviews

➖➖➖

6️⃣ Real-world machine learning projects

◀️ Learning how to build and deploy models.

➖➖➖

7️⃣ Designing machine learning systems

◀️ How to design a scalable and stable ML system.

➖➖➖

8️⃣ Machine Learning Mathematics

◀️ Basic mathematical concepts necessary to understand machine learning.

➖➖➖

9️⃣ Introduction to Statistical Learning

◀️ Learn algorithms with practical examples.

➖➖➖

1️⃣ Machine learning with a probabilistic approach

◀️ Better understanding modeling and uncertainty with a statistical perspective.

➖➖➖

1️⃣ UBC Machine Learning

◀️ Deep understanding of machine learning concepts with conceptual teaching from one of the leading professors in the field of ML,

➖➖➖

1️⃣ Deep Learning with Andrew Ng

◀️ A strong start in the world of neural networks, CNNs and RNNs.

➖➖➖

1️⃣ Linear Algebra with 3Blue1Brown

◀️ Intuitive and visual teaching of linear algebra concepts.

➖➖➖

🔴 Machine Learning Course

◀️ A combination of theory and practical training to strengthen ML skills.

➖➖➖

1️⃣ Mathematical Optimization with Python

◀️ You will learn the basic concepts of optimization with Python code.

➖➖➖

1️⃣ Explainable models in machine learning

◀️ Making complex models understandable.

➖➖➖

⚫️ Data Analysis with Python

◀️ Data analysis skills using Pandas and NumPy libraries.

#DataScience #MachineLearning #DeepLearning #Python #AI #MLProjects #DataAnalysis #ExplainableAI #100DaysOfCode #TechEducation #MLInterviewPrep #NeuralNetworks #MathForML #Statistics #Coding #AIForEveryone #PythonForDataScience

⚡️ BEST DATA SCIENCE CHANNELS ON TELEGRAM 🌟

Zep: A Temporal Knowledge Graph Architecture for Agent Memory

20 Jan 2025 · Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais, Jack Ryan, Daniel Chalef ·

We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core component Graphiti -- a temporally-aware knowledge graph engine that dynamically synthesizes both unstructured conversational data and structured business data while maintaining historical relationships. In the DMR benchmark, which the MemGPT team established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep's capabilities are further validated through the more challenging LongMemEval benchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such as cross-session information synthesis and long-term context maintenance, demonstrating Zep's effectiveness for deployment in real-world applications.

Paper: https://arxiv.org/pdf/2501.13956v1.pdf

Code: https://github.com/getzep/graphiti

⚡️ BEST DATA SCIENCE CHANNELS ON TELEGRAM 🌟

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

2 Apr 2025 · Shaojin Wu, Mengqi Huang, Wenxu Wu, Yufeng Cheng, Fei Ding, Qian He ·

Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.

Paper: https://github.com/bytedance/uno

Code: https://paperswithcode.com/dataset/dreambench

Dataset: DreamBooth

⚡️ BEST DATA SCIENCE CHANNELS ON TELEGRAM 🌟

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

31 Mar 2025 · Bang Liu, Xinfeng Li, et.

The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable of sophisticated reasoning, robust perception, and versatile action across diverse domains. As these agents increasingly drive AI research and practical applications, their design, evaluation, and continuous improvement present intricate, multifaceted challenges. This survey provides a comprehensive overview, framing intelligent agents within a modular, brain-inspired architecture that integrates principles from cognitive science, neuroscience, and computational research. We structure our exploration into four interconnected parts. First, we delve into the modular foundation of intelligent agents, systematically mapping their cognitive, perceptual, and operational modules onto analogous human brain functionalities, and elucidating core components such as memory, world modeling, reward processing, and emotion-like systems. Second, we discuss self-enhancement and adaptive evolution mechanisms, exploring how agents autonomously refine their capabilities, adapt to dynamic environments, and achieve continual learning through automated optimization paradigms, including emerging AutoML and LLM-driven optimization strategies. Third, we examine collaborative and evolutionary multi-agent systems, investigating the collective intelligence emerging from agent interactions, cooperation, and societal structures, highlighting parallels to human social dynamics. Finally, we address the critical imperative of building safe, secure, and beneficial AI systems, emphasizing intrinsic and extrinsic security threats, ethical alignment, robustness, and practical mitigation strategies necessary for trustworthy real-world deployment.

Paper: https://arxiv.org/pdf/2504.01990v1.pdf

Code: https://github.com/foundationagents/awesome-foundation-agents

⚡️ BEST DATA SCIENCE CHANNELS ON TELEGRAM 🌟

This channels is for Programmers, Coders, Software Engineers.

0️⃣ Python
1️⃣ Data Science
2️⃣ Machine Learning
3️⃣ Data Visualization
4️⃣ Artificial Intelligence
5️⃣ Data Analysis
6️⃣ Statistics
7️⃣ Deep Learning
8️⃣ programming Languages

✅ https://t.iss.one/addlist/8_rRW2scgfRhOTc0

✅ https://t.iss.one/Codeprogrammer