Related papers: Actor Continuation Passing: Efficient and Extensib…
In this paper, we propose to incorporate the blackboard architecture into LLM multi-agent systems (MASs) so that (1) agents with various roles can share all the information and others' messages during the whole problem-solving process, (2)…
Elasticity is highly desirable for stream processing systems to guarantee low latency against workload dynamics, such as surges in data arrival rate and fluctuations in data distribution. Existing systems achieve elasticity following a…
While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logical consistency, and smooth character development, often producing monotonous scripts with…
Distributed Stream Processing frameworks are being commonly used with the evolution of Internet of Things(IoT). These frameworks are designed to adapt to the dynamic input message rate by scaling in/out.Apache Storm, originally developed by…
Large language model (LLM)-based multi-agent systems have demonstrated impressive capabilities in handling complex tasks. However, the complexity of agentic behaviors makes these systems difficult to understand. When failures occur,…
Cloud developers have to build applications that are resilient to failures and interruptions. We advocate for a fault-tolerant programming model for the cloud based on actors, retry orchestration, and tail calls. This model builds upon…
Continuous reasoning has proven effective in incrementally analysing changes in application codebases within Continuous Integration/Continuous Deployment (CI/CD) software release pipelines. In this article, we present a novel declarative…
With the integration of massive distributed energy resources and the widespread participation of novel market entities, the operation of active distribution networks (ADNs) is progressively evolving into a complex multi-scenario,…
Dataflow devices represent an avenue towards saving the control and data movement overhead of Load-Store Architectures. Various dataflow accelerators have been proposed, but how to efficiently schedule applications on such devices remains…
The next generation of AI applications will continuously interact with the environment and learn from these interactions. These applications impose new and demanding systems requirements, both in terms of performance and flexibility. In…
Prompt engineering for LLMs remains complex, with existing frameworks either hiding complexity behind restrictive APIs or providing inflexible canned patterns that resist customization -- making sophisticated agentic programming…
The paper presents structures and techniques aimed towards co-designing scalable asynchronous and decentralized dynamic graph processing for fine-grain memory-driven architectures. It uses asynchronous active messages, in the form of…
In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can interact with streaming data: AI agents. Unlike traditional programs, AI agents use LLM reasoning to accomplish high-level tasks…
Involving humans directly for the benefit of AI agents' training is getting traction thanks to several advances in reinforcement learning and human-in-the-loop learning. Humans can provide rewards to the agent, demonstrate tasks, design a…
In this paper, we propose to develop service model architecture by merging multi-agentsystems and semantic web technology. The proposed architecture works in two stages namely, Query Identification and Solution Development. A person…
Agents in an open system communicate using interaction protocols. Suppose that we have a system of agents and that we want to add a new protocol that all (or some) agents should be able to understand. Clearly, modifying the source code for…
Following the ideas of the Remote Procedure Call model, we have developed a logic programming counterpart, naturally called Prolog Remote Predicate Call (Prolog RPC). The Prolog RPC protocol facilitates the integration of Prolog code in…
The message-driven nature of actors lays a foundation for developing scalable and distributed software. While the actor itself has been thoroughly modeled, the message passing layer lacks a common definition. Properties and guarantees of…
In E-learning, there is still the problem of knowing how to ensure an individualized and continuous learner's follow-up during learning process, indeed among the numerous tools proposed, very few systems concentrate on a real time learner's…
This paper argues for an accelerator development toolchain that takes into account the whole system containing the accelerator. With whole-system visibility, the toolchain can better assist accelerator scoping and composition in the context…