相关论文: app.build: A Production Framework for Scaling Agen…
Mobile agents research is clearly aiming towards imposing agent based development as the next generation of tools for writing software. This paper comes with its own contribution to this global goal by introducing a novel unifying framework…
LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging…
Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction…
Scaling up executable code data is significant for improving language models' software engineering capability. The intricate nature of the process makes it labor-intensive, time-consuming and expert-knowledge-dependent to build a large…
Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…
The rise of Large Language Models (LLMs) as coding agents promises to accelerate software development, but their impact on generated code reproducibility remains largely unexplored. This paper presents an empirical study investigating…
Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on natural language instructions. The increasing accuracy of…
With ChatGPT-like large language models (LLM) prevailing in the community, how to evaluate the ability of LLMs is an open question. Existing evaluation methods suffer from following shortcomings: (1) constrained evaluation abilities, (2)…
Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, Semantic Kernel, Strands, and LlamaIndex. All follow the same pattern: an external…
The conventional BIM authoring process typically requires designers to master complex and tedious modeling commands in order to materialize their design intentions within BIM authoring tools. This additional cognitive burden complicates the…
Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication…
Software code generation using Large Language Models (LLMs) is one of the most successful applications of modern artificial intelligence. Foundational models are very effective for popular frameworks that benefit from documentation,…
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models…
Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production. Recent large language models can accelerate this work, and recent benchmarks…
AI agentic programming is an emerging paradigm where large language model (LLM)-based coding agents autonomously plan, execute, and interact with tools such as compilers, debuggers, and version control systems. Unlike conventional code…
Developing full-stack web applications is complex and time-intensive, demanding proficiency across diverse technologies and frameworks. Although recent advances in multimodal large language models (MLLMs) enable automated webpage generation…
Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill…
Post-Training Multimodal Large Language Models (MLLMs) to build interactive agents holds promise across domains such as computer-use, web navigation, and robotics. A key challenge in scaling such post-training is lack of high-quality…
We introduce AI2Apps, a Visual Integrated Development Environment (Visual IDE) with full-cycle capabilities that accelerates developers to build deployable LLM-based AI agent Applications. This Visual IDE prioritizes both the Integrity of…
Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed agents' performance, especially the functionality for agent topology, tools, and memory.…