Related papers: Beyond Language Barriers: Multi-Agent Coordination…

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…

Large Language Models (LLMs) have demonstrated remarkable capabilities in solving various tasks, yet they often struggle with comprehensively addressing complex and vague problems. Existing approaches, including multi-agent LLM systems,…

Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the…

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…

The prominent large language models (LLMs) of today differ from past language models not only in size, but also in the fact that they are trained on a combination of natural language and formal language (code). As a medium between humans…

Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing…

Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot routing: they select a model once and return its output…

Large Language Models (LLMs) have made significant progress in handling complex programming tasks. However, current methods rely on manual model selection and fixed workflows, which limit their ability to adapt to changing task…

With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing…

Large Language Model (LLM) based coding tools have been tremendously successful as software development assistants, yet they are often designed for general purpose programming tasks and perform poorly for more specialized domains such as…

Emerging 6G networks rely on complex cross-layer optimization, yet manually translating high-level intents into mathematical formulations remains a bottleneck. While Large Language Models (LLMs) offer promise, monolithic approaches often…

Cutting-edge LLMs have emerged as powerful tools for multilingual communication and understanding. However, LLMs perform worse in Common Sense Reasoning (CSR) tasks when prompted in low-resource languages (LRLs) like Hindi or Swahili…

The rise of Large Language Models (LLMs) has redefined Machine Translation (MT), enabling context-aware and fluent translations across hundreds of languages and textual domains. Despite their remarkable capabilities, LLMs often exhibit…

The development of large language models (LLM) has shown progress on reasoning, though studies have largely considered either English or simple reasoning tasks. To address this, we introduce a multilingual structured reasoning and…

Medical Decision-Making (MDM) is a multi-faceted process that requires clinicians to assess complex multi-modal patient data patient, often collaboratively. Large Language Models (LLMs) promise to streamline this process by synthesizing…

Large language models and AI agents have recently shown promise in automating software performance optimization, but existing approaches predominantly rely on local, syntax-driven code transformations. This limits their ability to reason…

Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency.…

Code synthesis, which requires a deep understanding of complex natural language problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests,…

This paper shows that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer-based masked language model on one hundred languages,…

Large Language Models (LLMs) achieve competitive results compared to human experts in medical examinations. However, it remains a challenge to apply LLMs to complex clinical decision-making, which requires a deep understanding of medical…