Related papers: Confucius Code Agent: Scalable Agent Scaffolding f…
Agentic systems, in which diverse agents cooperate to tackle challenging problems, are exploding in popularity in the AI community. However, existing agentic frameworks take a relatively narrow view of agents, apply a centralized model, and…
The rise of AI agents is transforming how software can be built. The promise of agents is that developers might write code quicker, delegate multiple tasks to different agents, and even write a full piece of software purely out of natural…
Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm. Distinct from previous code generation techniques, code generation agents are characterized by three core features. 1)…
The beginning of the 21st century has seen many projects on distributed hash tables, both research and commercial. One of their aims has been to replace the first generation of file sharing software with scalable peer-to-peer architectures.…
Developing trustworthy multi-agent systems for practical applications is challenging due to the complicated communication of situational awareness (SA) among agents. This paper showcases a novel efficient and easy-to-use software framework…
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…
Code-generating tools are increasingly used in software development, yet experience reports on conversational "vibe coding" under production constraints remain limited. This paper presents an experience report from a small full-stack team…
Enterprise teams building internal coding agents face a gap between prototype performance and production readiness. The root cause is that technical model quality alone is insufficient -- tool design, safety enforcement, state management,…
The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…
General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reasoning, web interaction, coding, and autonomous research capabilities. However, current agent…
The Microservices Architecture (MSA) design pattern has become a staple for modern applications, allowing functionalities to be divided across fine-grained microservices, fostering reusability, distribution, and interoperability. As…
Enhancement of technology-based system support for knowledge workers is an issue of great importance. The "Knowledge work Support System (KwSS)" framework analyzes this issue from a holistic perspective. KwSS proposes a set of design…
Custom CUDA kernel development is essential for maximizing GPU utilization in large-scale distributed LLM training and inference, yet manually writing kernels that jointly leverage both computation and communication remains a…
The evolution of Large Language Models (LLMs) has shifted mobile computing from App-centric interactions to system-level autonomous agents. Current implementations predominantly rely on a "Screen-as-Interface" paradigm, which inherits…
Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code remains underexplored. Due to the size and complexities of systems code, making changes to a systems…
Frontier software engineering agents have saturated short-horizon benchmarks while regressing on the work that constitutes senior engineering: long-horizon, multi-engineer, ambiguous-specification deliverables. This paper takes a position…
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to…
Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE)…
Autonomous agents based on Large Language Models (LLMs) have evolved from reactive assistants to systems capable of planning, executing actions via tools, and iterating over environment observations. However, they remain vulnerable to…
AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and…