Related papers: Divide, Optimize, Merge: Fine-Grained LLM Agent Op…

Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks while it remains challenging for them to solve complex multi-step tasks as agents. In practice, agents sensitive to the outcome of certain key steps…

Nowadays, Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications. However, long context training poses great challenges considering the constraint of GPU memory. It not only leads…

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing…

Big data processing at the production scale presents a highly complex environment for resource optimization (RO), a problem crucial for meeting performance goals and budgetary constraints of analytical users. The RO problem is challenging…

Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks. L2O paradigms achieve great outcomes, e.g., refitting optimizer, generating unseen solutions iteratively or directly. However, conventional L2O…

Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thought (CoT) have further elevated their performance in handling complex logical problems.…

Optimising deep neural networks is a challenging task due to complex training dynamics, high computational requirements, and long training times. To address this difficulty, we propose the framework of Generalisable Agents for Neural…

Large Language Models (LLM) and foundation models are popular as they offer new opportunities for individuals and businesses to improve natural language processing, interact with data, and retrieve information faster. However, training or…

Supervised fine-tuning (SFT) has become an essential step in tailoring large language models (LLMs) to align with human expectations and specific downstream tasks. However, existing SFT methods typically treat each training instance as a…

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most…

Prompt engineering is pivotal for harnessing the capabilities of large language models (LLMs) across diverse applications. While existing prompt optimization methods improve prompt effectiveness, they often lead to prompt drifting, where…

This paper proposes an algorithm for Federated Learning (FL) with a two-layer structure that achieves both variance reduction and a faster convergence rate to an optimal solution in the setting where each agent has an arbitrary probability…

Large Language Models (LLMs) have achieved strong performance on a wide range of complex reasoning tasks, yet further gains are often possible by leveraging the complementary strengths of multiple models. While multi-agent frameworks can…

Large-scale optimization is a key backbone of modern business decision-making. However, building these models is often labor-intensive and time-consuming. We address this by proposing LEAN-LLM-OPT, a LightwEight AgeNtic workflow…

Large Language Model (LLM) agents have demonstrated impressive capabilities in handling complex interactive problems. Existing LLM agents mainly generate natural language plans to guide reasoning, which is verbose and inefficient. NL plans…

Generating performant executables from high level languages is critical to software performance across a wide range of domains. Modern compilers perform this task by passing code through a series of well-studied optimizations at…

This study analyzes the performance of domain-specific Large Language Models (LLMs) for the medical field by integrating Retrieval-Augmented Generation (RAG) systems within a federated learning framework. Leveraging the inherent advantages…

Inference scaling further accelerates Large Language Models (LLMs) toward Artificial General Intelligence (AGI), with large-scale Reinforcement Learning (RL) to unleash long Chain-of-Thought reasoning. Most contemporary reasoning approaches…

Aligning Large Language Models (LLMs) with human values often involves balancing multiple, conflicting objectives such as helpfulness and harmlessness. Training these models is computationally intensive, and centralizing the process raises…

Large language models (LLMs) have significantly advanced human language understanding and generation, with pretraining data quality and organization being crucial to their performance. Multi-stage pretraining is a promising approach, but…