Related papers: SKILLFOUNDRY: Building Self-Evolving Agent Skill L…
Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, yet remain confined to narrow domains requiring substantial human…
Despite rapid progress in large language model (LLM)-based multi-agent systems, current benchmarks fall short in evaluating their scalability, robustness, and coordination capabilities in complex, dynamic, real-world tasks. Existing…
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;…
In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…
Large language models (LLMs) have enabled remarkable advances in automated task-solving with multi-agent systems. However, most existing LLM-based multi-agent approaches rely on predefined agents to handle simple tasks, limiting the…
The emergence of LLMs has catalyzed a paradigm shift in autonomous agent development, enabling systems capable of reasoning, planning, and executing complex multi-step tasks. However, existing agent frameworks often suffer from…
A significant challenge facing researchers in the area of multi-agent reinforcement learning (MARL) pertains to the identification of a library that can offer fast and compatible development for multi-agent tasks and algorithm combinations,…
The transition from human-centric to agent-centric software development practices is disrupting existing knowledge sharing environments for software developers. Traditional peer-to-peer repositories and developer communities for shared…
Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag…
Multimodal agents are making rapid progress on general computer-use tasks, yet existing benchmarks remain largely confined to browsers and basic desktop applications, falling short in professional software workflows that dominate real-world…
Progress in science is deeply bound to the effective use of high-performance computing infrastructures and to the efficient extraction of knowledge from vast amounts of data. Such data comes from different sources that follow a cycle…
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…
Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid…
Knowledge infrastructures are defined as robust networks of people, artifacts, and institutions that generate, share and maintain specific knowledge. Yet, many domains are fragmented and far from robustly networked, such as science…
Conversational agents are increasingly deployed in knowledge-intensive settings, where correct behavior depends on retrieving and applying domain-specific knowledge from large, proprietary, and unstructured corpora during live interactions…
Industrial cyber physical systems operate under heterogeneous sensing, stochastic dynamics, and shifting process conditions, producing data that are often incomplete, unlabeled, imbalanced, and domain shifted. High-fidelity datasets remain…
Recent advances in code generation models have demonstrated impressive capabilities in automating software development tasks, yet these models still struggle in real-world software engineering scenarios. Although current training methods,…
Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large annotated datasets scientists often lack, while manual code…
Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and environments. We argue this focus on data volume overlooks a…
Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex $n$-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains…