Related papers: SkillGen: Verified Inference-Time Agent Skill Synt…

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based…

As multi-agent systems powered by Large Language Models (LLMs) are increasingly adopted in real-world workflows, users with diverse technical backgrounds are now building and refining their own agentic processes. However, these systems can…

Recent advances in LLM-based multi-agent systems (MAS) show that workflows composed of multiple LLM agents with distinct roles, tools, and communication patterns can outperform single-LLM baselines on complex tasks. However, most frameworks…

AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes…

In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under…

Post-training is essential for enabling large language models (LLMs) to follow human instructions. However, its effectiveness depends on high-quality instruction data, which is challenging to obtain in the real world due to privacy…

LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for…

LLM-based agents have demonstrated great potential in generating and managing code within complex codebases. In this paper, we introduce WebGen-Bench, a novel benchmark designed to measure an LLM-based agent's ability to create multi-file…

Requirements elicitation, a critical, yet time-consuming and challenging step in product development, often fails to capture the full spectrum of user needs. This may lead to products that fall short of expectations. This paper introduces a…

Text-to-video generation has been dominated by diffusion-based or autoregressive models. These novel models provide plausible versatility, but are criticized for improper physical motion, shading and illumination, camera motion, and…

Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point…

Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3D environments. While recent progress has been driven by large-scale pre-training and data…

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…

Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues…

Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often…

Agent Skills have become a practical way to extend LLM agents by packaging metadata, natural-language instructions, and executable resources into reusable capability bundles. However, this growing Skill ecosystem introduces a new compliance…

Traditional language-conditioned manipulation agent sequential adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practical deployment. In this paper, we propose SkillsCrafter, a…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Agent memory shapes how Large Language Model (LLM)-powered agents, akin to the human brain, progressively refine themselves through environment interactions. Existing paradigms remain constrained: parametric memory forcibly adjusts model…

Despite the rapid progress of large language models (LLMs), their length-controllable text generation (LCTG) ability remains below expectations, posing a major limitation for practical applications. Existing methods mainly focus on…