相关论文: SkillSmith: Compiling Agent Skills into Boundary-G…

The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new…

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We…

Effort estimation is a crucial activity in agile software development, where teams collaboratively review, discuss, and estimate the effort required to complete user stories in a product backlog. Current practices in agile effort estimation…

Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks. However, their efficacy is fundamentally constrained by static configurations governing agent behaviors,…

Metasurface inverse design has become central to realizing complex optical functionality, yet translating target responses into executable, solver-compatible workflows still demands specialized expertise in computational electromagnetics…

Simulations, although powerful in accurately replicating real-world systems, often remain inaccessible to non-technical users due to their complexity. Conversely, large language models (LLMs) provide intuitive, language-based interactions…

While frontier large language models (LLMs) are capable tool-using agents, current AI systems still operate in a strict turn-based fashion, oblivious to passage of time. This synchronous design forces user queries and tool-use to occur…

Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself,…

LLM agents benefit from reusable skills, yet test-time tasks often require guidance more specific than a static skill library can provide. We propose \emph{SkillTTA}, a Test-Time Adaptive Skill Synthesis method that retrieves a small set of…

We propose an intuitive LLM prompting framework (AgentKit) for multifunctional agents. AgentKit offers a unified framework for explicitly constructing a complex "thought process" from simple natural language prompts. The basic building…

Contemporary approaches to agent-based modeling (ABM) of social systems have traditionally emphasized rule-based behaviors, limiting their ability to capture nuanced dynamics by moving beyond predefined rules and leveraging contextual…

Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low…

Large language models (LLMs) are moving beyond static uses and are now powering agents that learn continually during their interaction with external environments. For example, agents can learn reusable skills while navigating web pages or…

Large Language Model agents demonstrate potential in solving real-world problems via tools, yet generalist intelligence is bottlenecked by scarce high-quality, long-horizon data. Existing methods collect privacy-constrained API logs or…

Agentic AI will be an essential enabling technology for designing future mobile communication systems, which could provide flexible and customized services, automate complex network operations, and drive autonomous decision-making across…

Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually convert research questions into workflow specifications, a…

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…

Large Language Model (LLM) agents are increasingly extended at runtime via skill packages, structured natural-language instruction bundles loaded from a well-known directory. Community install tooling and registries exist, but two gaps…

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…

Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often…