Related papers: Organizing, Orchestrating, and Benchmarking Agent …
Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI) agents have significantly automated data…
Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of…
Open-ended AI agents need to be able to learn efficiently goals of increasing complexity, abstraction and heterogeneity over their lifetime. Beyond sampling efficiently their own goals, autotelic agents specifically need to be able to keep…
This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the…
As large language models from diverse providers converge toward comparable benchmark performance, the traditional paradigm of selecting a single best model per task yields diminishing returns. We argue that orchestration topology -- the…
Agentic workflows have become the dominant paradigm for building complex AI systems, orchestrating specialized components, such as planning, reasoning, action execution, and reflection, to tackle sophisticated real-world tasks. However,…
Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bottleneck is the grounding gap in existing skill formulations:…
Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning. We argue…
Agentic AI systems, which leverage multiple autonomous agents and large language models (LLMs), are increasingly used to address complex, multi-step tasks. The safety, security, and functionality of these systems are critical, especially in…
Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks…
Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as an organizational abstraction, but we argue it is also a…
Reusable skills let LLM agents package task-specific procedures, tool affordances, and execution guidance into modular building blocks. As skill ecosystems grow to tens of thousands of entries, exposing every skill at inference time becomes…
The Agentic Service Ecosystem consists of heterogeneous autonomous agents (e.g., intelligent machines, humans, and human-machine hybrid systems) that interact through resource exchange and service co-creation. These agents, with distinct…
Large language model (LLM) powered AI agents have emerged as a promising paradigm for autonomous problem-solving, yet they continue to struggle with complex, multi-step real-world tasks that demand domain-specific procedural knowledge.…
Recent studies show that collaborating multiple large language model (LLM) powered agents is a promising way for task solving. However, current approaches are constrained by using a fixed number of agents and static communication…
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…
Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and…
Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-agent system (MAS) restructuring. This separation can create…
Multi-Agent Systems (MAS) built on large language models typically solve complex tasks by coordinating multiple agents through workflows. Existing approaches generates workflows either at task level or query level, but their relative costs…
Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a…