Awesome AI AgentsLLM Research Repositories

VoltAgent/awesome-ai-agent-papers

⭐ 1474 repository created 2026-02-10

Awesome AI Agent Papers is a curated bibliography maintained by the VoltAgent project that tracks research papers about the AI agent ecosystem published on arXiv from January 2026 onward. The maintainers review the weekly arXiv output, filter for papers directly relevant to agents, and sort them into five sections: Multi-Agent, covering coordination, communication topologies, negotiation, social simulation and meta-agent architectures; Memory and RAG; Eval and Observability; Agent Tooling; and AI Agent Security. At the time of the snapshot the list holds more than 360 papers, with roughly 53 entries under multi-agent, 57 under memory and RAG, 80 under evaluation and observability, 95 under agent tooling and 82 under security, and it is described as updated weekly. Each section is rendered as a collapsible table where every row gives the paper title linked to its arXiv PDF, a one to three sentence summary of what the paper investigates or claims, and a badge linking to the arXiv abstract page with the identifier. Summaries state the mechanism and, where the paper reports them, headline results, for example dynamic rewiring of agent-to-agent connections by semantic matching at each reasoning round, conformal prediction used to filter noisy inter-agent messages in multi-robot coordination, self-evolving long-running multi-agent systems built on shared persistent memory and asynchronous execution, benchmarks for buyer-seller negotiation between LLM agents, and analyses of emergent social structure among tens of thousands of autonomous agents on a social platform. The repository contains no code, only the annotated index in the README. It is aimed at engineers building agent systems, researchers surveying architectures and developers integrating LLM agents into products who want a filtered view of recent literature instead of raw arXiv feeds. Contributions come through pull requests, and the list follows the awesome list conventions.

https://github.com/VoltAgent/awesome-ai-agent-papers

awesome-listresearch-papersarxivmulti-agentagent-security

Also in LLM Research Repositories

elder-plinius/CL4R1T4S

CL4R1T4S is a project that provides transparency by collecting and sharing the hidden system prompts and guidelines used by major AI models and agents to promote trust and understanding of AI behavior.

WooooDyy/LLM-Agent-Paper-List

A comprehensive repository compiling essential academic papers and a detailed survey on the rise, framework, applications, and societal aspects of Large Language Model based AI agents.

mahseema/awesome-ai-tools

A curated repository listing top Artificial Intelligence tools across various categories including generative AI, chatbots, search engines, and writing assistants.

filipecalegario/awesome-generative-ai

A curated and comprehensive list of Generative AI tools, projects, models, artworks, and educational resources, regularly updated to reflect the latest advancements in the field.

DSXiangLi/DecryptPrompt

DecryptPrompt is a comprehensive resource hub that summarizes prompt and LLM research papers, open-source datasets and models, and AIGC applications, providing in-depth tutorials and analyses for AI researchers and practitioners.

zjunlp/LLMAgentPapers

LLMAgentPapers is a curated repository of essential academic papers on Large Language Model agents, covering topics from agent personality to multi-agent systems and applications.

luo-junyu/Awesome-Agent-Papers

A comprehensive and up-to-date research collection of papers on Large Language Model (LLM) agents, covering methodologies, applications, challenges, and key categories such as construction, collaboration, evolution, tools, security, benchmarks, and real-world applications.

webfuse-com/awesome-autoresearch

Curated index of autonomous improvement loops and research-agent systems descended from karpathy/autoresearch, grouped into general-purpose forks, research systems, platform ports, domain adaptations and benchmarks.