Related papers: RefEvo: Agentic Design with Co-Evolutionary Verifi…

Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only…

Large Language Models (LLMs) have shown remarkable performance in automated code generation. However, existing approaches often rely heavily on pre-defined test cases, which become impractical in scenarios where such cases are unavailable.…

Software engineers resolving repository-level issues do not treat existing tests as immutable correctness oracles. Instead, they iteratively refine both code and the tests used to characterize intended behavior, as new modifications expose…

Inference-time computation is a critical yet challenging paradigm for enhancing the reasoning performance of large language models (LLMs). While existing strategies improve reasoning stability and consistency, they suffer from notable…

The discovery of symbolic solutions -- mathematical expressions, logical rules, and algorithmic structures -- is fundamental to advancing scientific and engineering progress. However, traditional methods often struggle with search…

The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design automation has gained new momentum with the rise of large…

To evaluate the repository-level code generation capabilities of Large Language Models (LLMs) in complex real-world software development scenarios, many evaluation methods have been developed. These methods typically leverage contextual…

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models. However, existing methods rely solely on outcome rewards, without explicitly optimizing verification or leveraging…

Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to…

Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference. This setting raises a central question: how can an agent…

Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates…

Large language models are transforming systems research by automating the discovery of performance-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions that meet the stringent correctness…

Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a "passive accumulation" paradigm,…

Large Language Models (LLMs) have become pivotal tools for automating code generation in software development. However, these models face significant challenges in producing version-aware code for rapidly evolving languages like Rust, where…

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…

Large language models (LLMs) are increasingly deployed as conversational tutors in STEM education, yet most systems still rely on a single LLM with a static retrieval-augmented generation (RAG) pipeline over course materials. This design…

Acquiring high-quality instruction-code pairs is essential for training Large Language Models (LLMs) for code generation. Manually curated data is expensive and inherently limited in scale, motivating the development of code-centric…

The transition from sequential to parallel computing is essential for modern high-performance applications but is hindered by the steep learning curve of concurrent programming. This challenge is magnified for irregular data structures…

Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill…