Related papers: Inside the Scaffold: A Source-Code Taxonomy of Cod…
Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…
Modern coding scaffolds turn LLMs into capable software agents, but their ability to follow scaffold-specified instructions remains under-examined, especially when constraints are heterogeneous and persist across interactions. To fill this…
Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on…
Large language models (LLMs) have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into patching systems. While prior work explores prompting strategies and individual agent designs,…
Large Language Model (LLM)-based code analysis tools are adopted to automate software documentation tasks. However, the scalability of these approaches to real codebases, where Intermediate Representations (IR) exceed LLM context limits,…
Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce…
AI agent systems increasingly rely on reusable non-LLM engineering infrastructure that packages tool mediation, context handling, delegation, safety control, and orchestration. Yet the architectural design decisions in this surrounding…
Large language models (LLMs) have revolutionized the field of artificial intelligence, endowing it with sophisticated language understanding and generation capabilities. However, when faced with more complex and interconnected tasks that…
Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with distributed information, rather than merely…
This survey organizes the intricate literature on the design and optimization of emerging structures around post-trained LMs. We refer to this overarching structure as scaffolded LMs and focus on LMs that are integrated into multi-step…
Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…
Causal discovery through experimentation and intervention is fundamental to robust problem solving. It requires not just updating beliefs within a fixed framework but revising the hypothesis space itself, a capacity current AI agents lack…
Hierarchical multi-agent systems (HMAS) organize collections of agents into layered structures that help manage complexity and scale. These hierarchies can simplify coordination, but they also can introduce trade-offs that are not always…
Large Language Model (LLM) agents are increasingly proposed to automate offensive security tasks, with recent studies reporting near human-level success rates in Capture-the-Flag (CTF) challenges. We here revisit these results, providing a…
Recent advances in large language models (LLMs) have enabled a new class of AI agents that automate multiple stages of the data science workflow by integrating planning, tool use, and multimodal reasoning across text, code, tables, and…
Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm. Distinct from previous code generation techniques, code generation agents are characterized by three core features. 1)…
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…
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code…
Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…
The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical…