paper-with-me

Papers

TaskWeaver: A Code-First Agent Framework

2023-11-29 · Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang

Large Language Models (LLMs) have shown impressive abilities in natural language understanding and generation, leading to their widespread use in applications such as chatbots and virtual assistants. However, existing LLM frameworks face limitations in handling domain-specific data analytics tasks with rich data structures. Moreover, they struggle with flexibility to meet diverse user requirements. To address these issues, TaskWeaver is proposed as a code-first framework for building LLM-powered autonomous agents. It converts user requests into executable code and treats user-defined plugins as callable functions. TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic. It also incorporates domain-specific knowledge through examples and ensures the secure execution of generated code. TaskWeaver offers a powerful and flexible framework for creating intelligent conversational agents that can handle complex tasks and adapt to domain-specific scenarios. The code is open sourced at https://github.com/microsoft/TaskWeaver/.

📄 PDF Abstract BibTeX arXiv:2311.17541

Code (1)

microsoft/taskweaver 공식 구현

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

Introducing Consort: A Spec-First Agent Framework for Enforced, Test-Driven Development on Live Database Branches

2026-09-09 · Kevin Hartman arxiv

When an agent writes code, the development framework becomes the control system for a non-deterministic worker. Spec-first, agent-driven frameworks have gained rapid traction since 2025; the installable ones, GitHub Spec…

AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering

2026-04-13 · Rajesh Kumar, Waqar Ali, Junaid Ahmed, Najma Imtiaz Ali 외 arxiv

Large language models generate plausible code but cannot verify correctness. Existing multi-agent systems simulate execution or leave verification optional. We introduce execution-grounded verification as a first-class p…

TDD-Agent: Test-Driven Reasoning for Code Generation

2026-08-17 · Hongyue Yu, Kefan Li, Jiakun Li, Hongzheng Chai 외 arxiv

Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging. Existing approaches often use generated tests as static …

Code Generation

AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation

2025-07-26 · Sourena Khanzadeh arxiv

Software development is a complex, multi-phase process traditionally requiring collaboration among individuals with diverse expertise. We propose AgentMesh, a Python-based framework that uses multiple cooperating LLM-pow…

Code Generation

QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction

2023-06-18 · Zikang Zhou, Zihao Wen, JianPing Wang, Yung-Hui Li 외

Estimating the joint distribution of on-road agents' future trajectories is essential for autonomous driving. In this technical report, we propose a next-generation framework for joint multi-agent trajectory prediction c…

Autonomous DrivingDecoderMotion ForecastingPrediction+2