Related papers: Scaling Coding Agents via Atomic Skills
How can we build generalist robot systems? Scale may not be enough due to the significant multimodality of robotics tasks, lack of easily accessible data and the challenges of deploying on physical hardware. Meanwhile, most deployed robotic…
Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit…
Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…
LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environments. This paper provides the first comprehensive survey of evaluation methods for these…
Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning…
Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein multiple agents collaborate and communicate with each other,…
Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer workflows. Existing benchmarks often focus on algorithmic…
As code large language models (LLMs) evolve into tool-interactive agents via the Model Context Protocol (MCP), their generalization is increasingly limited by low-quality synthetic data and the diminishing returns of quantity scaling.…
Training large language models to acquire specific skills remains a challenging endeavor. Conventional training approaches often struggle with data distribution imbalances and inadequacies in objective functions that do not align well with…
We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that…
Agent skills extend large language model (LLM) agents with reusable, program-like modules that define triggering conditions, procedural logic, and tool interactions. As these skills proliferate in public marketplaces, it is unclear what…
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,…
We introduce a novel paradigm for robot pro- gramming with which we aim to make robot programming more accessible for unexperienced users. In order to do so we incorporate two major components in one single framework: autonomous skill…
Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these…
Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…
Resolving team conflicts requires not only task-specific competence, but also social intelligence to find common ground and build consensus. As AI agents increasingly collaborate on complex work, they must develop coordination capabilities…
Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…
The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…
Coding agents powered by large language models (LLMs) have gained traction for automating code generation through iterative problem-solving with minimal human involvement. Despite the emergence of various frameworks, e.g., LangChain,…
This paper investigates code LLMs' capability of static analysis during code intelligence tasks such as code summarization and generation. Code LLMs are now household names for their abilities to do some programming tasks that have…