Related papers: SAFEdit: Does Multi-Agent Decomposition Resolve th…
Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.…
The advancement of natural language processing (NLP) has been significantly boosted by the development of transformer-based large language models (LLMs). These models have revolutionized NLP tasks, particularly in code generation, aiding…
Large language model agents often fail to accumulate knowledge from experience, treating each task as an independent challenge. Recent methods extract experience as flattened textual knowledge, which cannot capture procedural logic of…
Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely…
Training AI models has always been challenging, especially when there is a need for custom models to provide personalized services. Algorithm engineers often face a lengthy process to iteratively develop models tailored to specific business…
Efficiently updating multilingual knowledge in large language models (LLMs), while preserving consistent factual representations across languages, remains a long-standing and unresolved challenge. While deploying separate editing systems…
Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing benchmarks focus predominantly on single-issue bug fixes…
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to…
Refactoring is a constant activity in software development and maintenance. Scale and maintain software systems are based on code refactoring. However, this process is still labor intensive, as it requires programmers to analyze the…
Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…
Students benefit from math problems contextualized to their interests. Large language models (LLMs) offer promise for efficient personalization at scale. However, LLM-generated personalized problems may often have problems such as…
Establishing reliable and verifiable fingerprinting mechanisms is fundamental to controlling the unauthorized redistribution of large language models (LLMs). However, existing approaches face two major challenges: (a) ensuring…
Large Language Models (LLMs) have shown tremendous potential as agents, excelling at tasks that require multiple rounds of reasoning and interactions. Rejection Sampling Fine-Tuning (RFT) has emerged as an effective method for finetuning…
Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We…
Tool-augmented language agents frequently fail in real-world deployment due to tool malfunctions--timeouts, API exceptions, or inconsistent outputs--triggering cascading reasoning errors and task abandonment. Existing agent training…
Recent progress in multimodal foundation models has enabled Vision-Language Agents (VLAs) to decompose complex visual tasks into executable tool-based plans. While recent benchmarks have begun to evaluate iterative self-correction, its…
Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…
Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study of a multi-agent autonomous testing system evaluated using anonymized execution data from a…
Embodied instruction following (EIF) requires agents to understand and execute complex natural language commands within interactive 3D environments. Despite recent advances, existing methods often fail in long-horizon planning and handling…
Large language models (LLMs) have shown strong reasoning and coding capabilities, yet they struggle to generalize to real-world software engineering (SWE) problems that are long-horizon and out of distribution. Existing systems often rely…