相关论文: CoRe-Code: Collaborative Reinforcement Learning fo…

Large Language Models (LLMs) have demonstrated great promise in generating code, especially when used inside an evolutionary computation framework to iteratively optimize the generated algorithms. However, in some cases they fail to…

To optimize the reasoning and problem-solving capabilities of Large Language Models (LLMs), we propose a novel cloud-edge collaborative architecture that enables a structured multi-agent prompting framework. This framework comprises three…

Despite significant advancements in the general capability of large language models (LLMs), they continue to struggle with consistent and accurate reasoning, especially in complex tasks such as mathematical and code reasoning. One key…

Optimizing scientific software is a difficult task because codebases are often large and complex, and performance can depend upon several factors including the algorithm, its implementation, and hardware among others. Causes of poor…

Evaluating the performance of Code Language Models (CLMs) for software engineering tasks, especially in multilingual and low-resource programming language settings, poses significant challenges. These challenges are primarily due to the…

Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in external evidence. Despite its success, many existing RAG systems are built based on a…

Large Language Models (LLMs) have demonstrated superior listwise ranking performance. However, their superior performance often relies on large-scale parameters (\eg, GPT-4) and a repetitive sliding window process, which introduces…

While the complex reasoning capability of Large Language Models (LLMs) has attracted significant attention, single-agent systems often encounter inherent performance ceilings in complex tasks such as code generation. Multi-agent…

Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress for code generation. Recently, large language models (LLMs) have demonstrated remarkable…

Pre-trained Vision-Language Models (VLMs) are able to understand visual concepts, describe and decompose complex tasks into sub-tasks, and provide feedback on task completion. In this paper, we aim to leverage these capabilities to support…

Large Language Models (LLMs) have enabled multi-agent systems to perform autonomous code generation for complex tasks. Despite the recent growth in research and industrial applications in this area, there is little work on synthesizing…

Reasoning models (RMs), language models (LMs) trained with reinforcement learning to produce long-form natural language reasoning, have been remarkably successful, but they still require large amounts of computation and data to train, and…

Coding agents powered by large language models (LLMs) have gained traction for automating code generation through iterative problem-solving with minimal human involvement. Despite the emergence of various frameworks, e.g., LangChain,…

Recent advancement in code understanding and generation demonstrates that code LLMs fine-tuned on a high-quality instruction dataset can gain powerful capabilities to address wide-ranging code-related tasks. However, most previous existing…

Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental…

In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that…

Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as code generation. However, limited trajectory diversity often leads to diminishing returns, which constrains the achievable…

While Large Language Models (LLMs) excel in certain reasoning tasks, they struggle in multi-agent games where the final outcome depends on the joint strategies of all agents. In multi-agent games, the non-stationarity of other agents brings…

The development of Multimodal Virtual Agents has made significant progress through the integration of Multimodal Large Language Models. However, mainstream training paradigms face key challenges: Behavior Cloning is simple and effective…