Related papers: Don't Vibe Code, Do Skele-Code: Interactive No-Cod…
Multi-agent workflows have become an effective strategy for tackling complicated tasks by decomposing them into multiple sub-tasks and assigning them to specialized agents. However, designing optimal workflows remains challenging due to the…
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a…
Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…
We present NormCode Canvas (v1.1.3), a deployed system realizing Case-Based Reasoning at two levels for multi-step LLM workflows. The foundation is NormCode, a semi-formal planning language whose compiler-verified scope rule ensures every…
AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…
Iteratively refining and critiquing sketches are crucial steps to developing effective designs. We introduce Scones, a mixed-initiative, machine-learning-driven system that enables users to iteratively author sketches from text…
Most business process automation is still developed using traditional automation technologies such as workflow engines. These systems provide domain specific languages that require both business knowledge and programming skills to…
Software development is a cognitively intensive process requiring multitasking, adherence to evolving workflows, and continuous learning. With the rise of large language model (LLM)-based tools, such as conversational agents (CAs), there is…
AI Agents are changing the way work gets done, both in consumer and enterprise domains. However, the design patterns and architectures to build highly capable agents or multi-agent systems are still developing, and the understanding of the…
Agentic AI is poised to usher in a seismic paradigm shift in Software Engineering (SE). As technologists rush head-along to make agentic AI a reality, SE researchers are driven to establish agentic SE as a research area. While early visions…
UI-to-code aims to translate UI screenshots into executable front-end code. Despite progress with vision-language models (VLMs), most existing methods formulate UI-to-code as a single-pass generation, which mismatches real-world UI…
AI coding agents have become central to developer workflows, yet every existing solution locks its reasoning capabilities within a specific delivery form, such as a CLI, IDE plugin, or web application. This limitation creates systemic…
Sketches, with their expressive potential, allow humans to convey the essence of an object through even a rough contour. For the first time, we harness this expressive potential to improve segmentation performance in challenging tasks like…
Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often…
Contemporary multi-agent systems encounter persistent challenges in cross-platform interoperability, dynamic task scheduling, and efficient resource sharing. Agents with heterogeneous implementations often lack standardized interfaces;…
"Look before you leap"; "a stitch in time saves nine"; "more haste, less speed". Many proverbs declare the wisdom of planning before doing. We suggest how to apply this to Excel, by explaining and specifying spreadsheets before coding them,…
At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely…
Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification.…
We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them…