Related papers: BootstrapAgent: Distilling Repository Setup into R…

The primary value of AI agents in software development lies in their ability to extend the developer's capacity for reasoning and action, not to supplant human involvement. To showcase how to use agents working in tandem with developers, we…

In the first half of 2025, coding agents have emerged as a category of development tools that have very quickly transitioned to the practice. Unlike ''traditional'' code completion LLMs such as Copilot, agents like Cursor, Claude Code, or…

Code auditing is the process of reviewing code with the aim of identifying bugs. Large Language Models (LLMs) have demonstrated promising capabilities for this task without requiring compilation, while also supporting user-friendly…

With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop reasoning, which requires models to engage in deliberate thinking and multi-step interaction,…

Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task…

While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-based agents, which involve planning,…

Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…

The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks typically demand full-fledged code repositories rather than…

User models in information retrieval rest on a foundational assumption that observed behavior reveals intent. This assumption collapses when the user is an AI agent privately configured by a human operator. For any action an agent takes, a…

Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hinder reliability and maintainability. Unlike traditional…

Building state-of-the-art (SOTA) predictive models for drug discovery requires expensive search over tools, architectures, and training strategies. Current LLM-based agents can find SOTA solutions through extensive trial and error, but they…

Recent text-to-image generation models have demonstrated incredible success in generating images that faithfully follow input prompts. However, the requirement of using words to describe a desired concept provides limited control over the…

Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large codebases. Existing repository-level approaches process…

Software development agents powered by large language models (LLMs) have shown great promise in automating tasks like environment setup, issue solving, and program repair. Unfortunately, understanding and debugging such agents remain…

Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for…

This paper presents a novel approach for unified retrieval-augmented generation (RAG) systems using the recent emerging large language model (LLM) agent concept. Specifically, Agent LLM, which utilizes LLM as fundamental controllers, has…

Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, this paradigm overlooks two fundamental factors: the…

Many modern software systems are built as a set of autonomous software components (also called agents) that collaborate with each other and are situated in an environment. To keep these multiagent systems operational under abnormal…

This technical note presents a new approach to carrying out the kind of exploration achieved by Thompson sampling, but without explicitly maintaining or sampling from posterior distributions. The approach is based on a bootstrap technique…

Automated GUI testing is crucial for ensuring the quality and reliability of Android apps. However, the efficacy of existing UI testing techniques is often limited, especially in terms of coverage. Recent studies, including the…