Large Language Model (LLM) agents, capable of performing a broad range of actions, such as invoking tools and controlling robots, show great potential in tackling real-world challenges. LLM agents are typically prompted to produce actions by generating JSON or text in a pre-defined format, which is usually limited by constrained action space (e.g., the scope of pre-defined tools) and restricted flexibility (e.g., inability to compose multiple tools). This work proposes to use executable Python code to consolidate LLM agents' actions into a unified action space (CodeAct). Integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations through multi-turn interactions. Our extensive analysis of 17 LLMs on API-Bank and a newly curated benchmark shows that CodeAct outperforms widely used alternatives (up to 20% higher success rate). The encouraging performance of CodeAct motivates us to build an open-source LLM agent that interacts with environments by executing interpretable code and collaborates with users using natural language. To this end, we collect an instruction-tuning dataset CodeActInstruct that consists of 7k multi-turn interactions using CodeAct. We show that it can be used with existing data to improve models in agent-oriented tasks without compromising their general capability. CodeActAgent, finetuned from Llama2 and Mistral, is integrated with Python interpreter and uniquely tailored to perform sophisticated tasks (e.g., model training) using existing libraries and autonomously self-debug.
PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments
Hong Kong Baptist University（香港 Baptist 大学）；Independent Researcher（独立研究员）；HKUST（香港科技大学）；Beijing Institute of Technology（北京理工大学）；Southern University of Science and Technology（南方科技大学）；Wayne State University（韦恩州立大学）；University of Edinburgh（爱丁堡大学）
VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents
University of Science and Technology of China（中国科学技术大学）；iFLYTEK Research（iFLYTEK研究院）；Xiamen University（厦门大学）；University of Chinese Academy of Sciences（中国科学院大学）
SPADE: Self-Play in Adaptive Synthetic Executable Environments
University of Washington（华盛顿大学）；Stanford University（斯坦福大学）；Northeastern University（东北大学）；Carnegie Mellon University（卡内基梅隆大学）；Massachusetts Institute of Technology（麻省理工学院）；National University of Singapore（新加坡国立大学）；Seoul National University（首尔大学）；Stevens Institute of Technology（史蒂文斯理工学院）；University of Chicago（芝加哥大学）
AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
Fudan University（复旦大学）；Rhine AI（莱茵人工智能公司）；Shanghai University of Engineering and Science（上海工程技术大学）；Xiaohongshu Inc.（小红书公司）；Fudan-Aishu Cognitive Intelligence Joint Research Center（复旦-爱数认知智能联合研究中心）
Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents
The Hong Kong Polytechnic University（香港理工大学）；The University of Hong Kong（香港大学）；Zhejiang Normal University（浙江师范大学）；Research Institute for Generative AI, The Hong Kong Polytechnic University（香港理工大学生成式人工智能研究所）
SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown
The Hong Kong University of Science and Technology（香港科技大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Harbin Institute of Technology, Harbin（哈尔滨工业大学）
GenCoord: Executable Commitments for Embodied LLM Agents under Private Information
Tsinghua University（清华大学）；Beijing Normal-Hong Kong Baptist University（北京师范大学-香港浸会大学联合国际学院）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）；University of California San Diego（加利福尼亚大学圣迭戈分校）
CityPlanner: A Sandbox Agent for Executable Urban Planning
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；MIIT Key Laboratory of Data and Decision Intelligence, Beihang University（北京航空航天大学工业和信息化部数据与决策智能重点实验室）
Task-oriented conversational agents rely on semantic parsers to translate natural language to formal representations. In this paper, we propose the design and rationale of the ThingTalk formal representation, and how the design improves the development of transactional task-oriented agents. ThingTalk is built on four core principles: (1) representing user requests directly as executable statements, covering all the functionality of the agent, (2) representing dialogues formally and succinctly to support accurate contextual semantic parsing, (3) standardizing types and interfaces to maximize re…
