llmagents

[Up-to-date] Large Language Model Agent: A Survey on Methodology, Applications and Challenges

Autonomous Agents (LLMs) research papers. Updated Daily.

A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.

The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench

All the code and materials

[ICML 2025] Official resources of "KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search".

Official code of "The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets"

Source code for our paper: "Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents".

The LLMAgentOps Toolkit is a repository that provides a foundational structure for building LLM Agent-based applications using the Semantic Kernel. It serves as a starting point for data scientists and developers, facilitating experimentation, evaluation, and deployment of LLM Agent-based applications to production.

Enabling LLMs to Think Proactively and Initiate Dialogue with Consciousness. A multi-agent LLM architecture inspired by Global Workspace Theory (GWT) from cognitive science.

The official source code for "Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling" (ACL 2024, Findings)

How to build LLM agents with Magentic

MCP server built with Google’s Agent Development(ADK) Kit featuring multiple specialised agents that collaborate through intelligent routing. The system provides RESTful API endpoints for various capabilities including web searches, data analysis, and code generation while maintaining extensibility through a modular architecture

Code for Automated Profile Inference with Language Model Agents. ACL 2026

Simple Code Creator & Debugger using LLM Reflection

Automap is a agentic pipeline that leverages Large Language Models (LLMs) and LangGraph to automate the creation of RML mappings and Knowledge Graph materialization. The system uses a multi-agent architecture to analyze CSV schemas, scout ontologies, and iteratively refine YARRRML mappings before final execution.

LLM Agent Routing Project: This project implements a routing system for user queries using LangChain and Groq's Gemma2-9b-It model. The system intelligently routes questions to arxiv, Wikipedia, or an LLM based on the context, offering efficient and targeted responses for AI research, human information, or general queries.

Optimize frozen LLM agents for HotpotQA with reusable natural language skills trained through iterative validation cycles.

基于 AI 小说平台”叙界“的真实需求 AI 赛博斗蛐蛐