Related papers: Beyond Fixed Tests: Repository-Level Issue Resolut…

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning…

Improving the code generation capabilities of large language models (LLMs) typically relies on supervised fine-tuning or preference optimization, both of which require costly external resources such as powerful teacher models or reliable…

Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration…

Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM)-based AI agents. However, existing backbone RL algorithms lack verified convergence guarantees in agentic scenarios, especially in…

Language-driven generative agents have enabled large-scale social simulations with transformative uses, from interpersonal training to aiding global policy-making. However, recent studies indicate that generative agent behaviors often…

Software issue resolution aims to address real-world issues in software repositories (e.g., bug fixing and efficiency optimization) based on natural language descriptions provided by users, representing a key aspect of software maintenance.…

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…

Reformulating nonlinear optimization problems into solver-ready linear optimization problems is often necessary for practical applications, but the process is often manual and requires domain expertise. We propose LinearizeLLM, an…

We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as…

The rapid progress of large foundation models has accelerated the development of task-specialized agents across diverse domains. However, the effectiveness of agents remains tightly coupled with the quality of training data, while curating…

Large-language-model (LLM) agents exhibit complex, context-sensitive behaviour that quickly renders static benchmarks and ad-hoc manual testing obsolete. We present Neo, a configurable, multi-agent framework that automates realistic,…

Recent advancements in prompt engineering strategies, such as Chain-of-Thought (CoT) and Self-Discover, have demonstrated significant potential in improving the reasoning abilities of Large Language Models (LLMs). However, these…

Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric…

Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code…

Automatic program repair can be a challenging task, especially when resolving complex issues at a repository-level, which often involves issue reproduction, fault localization, code repair, testing and validation. Issues of this scale can…

A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this…

Software engineering activities such as package migration, fixing errors reports from static analysis or testing, and adding type annotations or other specifications to a codebase, involve pervasively editing the entire repository of code.…

Given that Large Language Models (LLMs) are increasingly applied to automate software development, comprehensive software assurance spans three distinct goals: regression prevention, reactive reproduction, and proactive discovery. Current…

Coding agents are increasingly deployed to autonomously maintain software, including to resolve user-reported issues: a bug report comes in and the agent creates a patch to address it. However, in any real-world deployment, they will…

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…