Related papers: Robust and Efficient Tool Orchestration via Layere…
Deep-learning-based intelligent services have become prevalent in cyber-physical applications including smart cities and health-care. Collaborative end-edge-cloud computing for deep learning provides a range of performance and efficiency…
Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on…
A compositional sheaf-theoretic framework for the modeling of complex event-based systems is presented. We show that event-based systems are machines, with inputs and outputs, and that they can be composed with machines of different types,…
In this paper, we focus on Dynamic Execution techniques that optimize the computation flow based on input. This aims to identify simpler problems that can be solved using fewer resources, similar to human cognition. The techniques discussed…
Intelligent robots need to generate and execute plans. In order to deal with the complexity of real environments, planning makes some assumptions about the world. When executing plans, the assumptions are usually not met. Most works have…
Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to static prompts and agent roles, rigid workflows, and…
Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and intrinsic…
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected…
Large language models (LLMs) are increasingly deployed as tool-augmented agents capable of executing system-level operations. While existing benchmarks primarily assess textual alignment or task success, less attention has been paid to the…
We introduce Orla, a library for constructing and running LLM-based agentic systems. Modern agentic applications consist of workflows that combine multiple LLM inference steps, tool calls, and heterogeneous infrastructure. Today, developers…
Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve performance -- focused sets of 2-3 skills outperform comprehensive documentation, and…
This paper introduces a model of multi-unit organizations with either static structures, i.e., they are designed top-down following classical approaches to organizational design, or dynamic structures, i.e., the structures emerge over time…
Modern agentic frameworks (e.g., CrewAI and AutoGen) have evolved into complex, autonomous multi-agent systems, introducing unique reliability challenges beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus…
The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions within the scope of pre-existing tools created by experts.…
Driven by Large Language Models, the single-agent, multi-tool architecture has become a popular paradigm for autonomous agents. However, this architecture introduces a severe privacy risk, which we term Tools Orchestration Privacy Risk…
Orchestrated multi-agent systems represent the next stage in the evolution of artificial intelligence, where autonomous agents collaborate through structured coordination and communication to achieve complex, shared objectives. This paper…
The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To…
Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment. Learning goal-conditioned policies is a natural paradigm to solve such tasks. However, current…
Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding…
The adoption of large language models (LLMs) for structured information extraction from financial documents has accelerated rapidly, yet production deployments face fundamental architectural decisions with limited empirical guidance. We…