Related papers: CodeDelegator: Mitigating Context Pollution via Ro…
Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse when downsized to…
Autonomous agents powered by large language models (LLMs) perform complex tasks through long-horizon reasoning and tool interaction, where a fundamental trade-off arises between execution efficiency and reasoning robustness. Models at…
Large Language Models (LLMs) have shown great ability in solving traditional natural language tasks and elementary reasoning tasks with appropriate prompting techniques. However, their ability is still limited in solving complicated science…
The rapid evolution of Large Language Model (LLM)-based autonomous agents is reshaping the digital landscape toward an emerging Agentic Web, where increasingly specialized agents must collaborate to accomplish complex tasks. However,…
We present Code Broker, a multi agent system built on Google s Agent Development Kit ADK that analyses Python source code from individual files, local directory trees, or remote GitHub repositories and generates structured, actionable…
Although Large Language Models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a…
In this work, we study Cooperative Spatial Intelligence, the ability of decentralized embodied agents to coordinate effectively under dynamic environmental constraints across city-scale outdoor domains. We introduce Sentinel Challenge, a…
Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally…
Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with…
Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…
Security Policies (SP) constitute the core of communication networks protection infrastructures. It offers a set of rules allowing differentiating between legitimate actions and prohibited ones and consequently, associates each entity in…
Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…
Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating execution…
Code reproduction is a cornerstone of scientific validity, yet it remains a formidable challenge in computer networking research due to the scarcity of open-source implementations and the complexity of heterogeneous system architectures.…
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often…
As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to another. While automatic code translation offers a promising solution, it has long…
Computational agents support humans in many areas of life and are therefore found in heterogeneous contexts. This means they operate in rapidly changing environments and can be confronted with huge state and action spaces. In order to…
In this paper we introduce ResearchCodeAgent, a novel multi-agent system leveraging large language models (LLMs) agents to automate the codification of research methodologies described in machine learning literature. The system bridges the…
Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and…
Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and…