Related papers: CodeMem: Architecting Reproducible Agents via Dyna…

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate…

As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult. This is…

Memory systems are widely adopted to enhance LLMs for long-horizon tasks, and are commonly organized as multi-agent pipelines with memory building, summarizing, and retrieval agents. To empower this system, existing RL-based methods either…

Multi-agent systems built on large language models (LLMs) are difficult to reason about. Coordination errors such as deadlocks or type-mismatched messages are often hard to detect through testing. We introduce a domain-specific language for…

Large Language Model (LLM) based agents have demonstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most research focuses on improving single-task performance, practical scenarios often involve…

Generative Artificial Intelligence (GenAI) has rapidly transformed various fields including code generation, text summarization, image generation and so on. Agentic AI is a recent evolution that further advances this by coupling the…

We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…

Solving mechanics problems using numerical methods requires comprehensive intelligent capability of retrieving relevant knowledge and theory, constructing and executing codes, analyzing the results, a task that has thus far mainly been…

AI agent development relies heavily on natural language prompting to define agents' tasks, knowledge, and goals. These prompts are interpreted by Large Language Models (LLMs), which govern agent behavior. Consequently, agentic performance…

Code generation aims to produce code that fulfills requirements written in natural languages automatically. Large language Models (LLMs) like ChatGPT have demonstrated promising effectiveness in this area. Nonetheless, these LLMs often fail…

AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…

We present Dynamic ReAct, a novel approach for enabling ReAct agents to efficiently operate with extensive Model Control Protocol (MCP) tool sets that exceed the contextual memory limitations of large language models. Our approach addresses…

Designing realistic and functional 3D indoor rooms is essential for a wide range of applications, including interior design, virtual reality, gaming, and embodied AI. While recent MLLM-based approaches have shown great potential for 3D room…

Large language models (LLMs) are rapidly evolving from passive engines of text generation into agentic entities that can plan, remember, invoke external tools, and co-operate with one another. This perspective paper investigates how such…

Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental \textit{Temporal Gap} between action initiation and completion. Existing…

This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges…

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over…

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon…

The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…

Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Language Models (LLMs) have demonstrated remarkable capabilities in code migration tasks. However, while research on…