paper-with-me

Papers

Nexus: Execution-Grounded Multi-Agent Test Oracle Synthesis

2025-10-30 · Dong Huang, Mingzhe Du, Jie M. Zhang, Zheng Lin, Meng Luo, Qianru Zhang, See-Kiong Ng arxiv

Test oracle generation in non-regression testing is a longstanding challenge in software engineering, where the goal is to produce oracles that can accurately determine whether a function under test (FUT) behaves as intended for a given input. In this paper, we introduce Nexus, a novel multi-agent framework to address this challenge. Nexus generates test oracles by leveraging a diverse set of specialized agents that synthesize test oracles through a structured process of deliberation, validation, and iterative self-refinement. During the deliberation phase, a panel of four specialist agents, each embodying a distinct testing philosophy, collaboratively critiques and refines an initial set of test oracles. Then, in the validation phase, Nexus generates a plausible candidate implementation of the FUT and executes the proposed oracles against it in a secure sandbox. For any oracle that fails this execution-based check, Nexus activates an automated selfrefinement loop, using the specific runtime error to debug and correct the oracle before re-validation. Our extensive evaluation on seven diverse benchmarks demonstrates that Nexus consistently and substantially outperforms state-of-theart baselines. For instance, Nexus improves the test-level oracle accuracy on the LiveCodeBench from 46.30% to 57.73% for GPT-4.1-Mini. The improved accuracy also significantly enhances downstream tasks: the bug detection rate of GPT4.1-Mini generated test oracles on HumanEval increases from 90.91% to 95.45% for Nexus compared to baselines, and the success rate of automated program repair improves from 35.23% to 69.32%.

📄 PDF Abstract BibTeX arXiv:2510.26423

Code (0)

등록된 구현이 없습니다.

Tasks

Program Repair

Similar Papers 제목 키워드 기반

Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System

2025-06-10 · Yuan Guo, Tingjia Miao, Zheng Wu, Pengzhou Cheng 외

Autonomous agents powered by multimodal large language models have been developed to facilitate task execution on mobile devices. However, prior work has predominantly focused on atomic tasks -- such as shot-chain execut…

Scheduling

Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration

2026-05-10 · Keqi Han, Songlin Zhao, Yao Su, Xiang Li 외 arxiv

Transforming neuroimaging data into clinically actionable biomarkers is a knowledge-intensive and labor-intensive process. Standardized workflows such as fMRIPrep have improved robustness and efficiency, but they are sta…

NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning

2026-05-10 · Tiehan Cui, Peipei Liu, Yanxu Mao, Congying Liu 외 arxiv

While Large Language Models (LLMs) have catalyzed progress in embodied intelligence, a fundamental gap between their inherent probabilistic uncertainty and the strict determinism and verifiable safety required in the phy…

Continual Learning

S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research

2026-02-02 · S1-NexusAgent Team arxiv

Modern scientific research relies on large-scale data, complex workflows, and specialized tools, which existing LLMs and tool-based agents struggle to handle due to limitations in long-horizon planning, robust goal maint…

Continual Learning

The Pursuit of Diversity: Multi-Objective Testing of Deep Reinforcement Learning Agents

2025-10-16 · Antony Bartlett, Cynthia Liem, Annibale Panichella arxiv

Testing deep reinforcement learning (DRL) agents in safety-critical domains requires discovering diverse failure scenarios. Existing tools such as INDAGO rely on single-objective optimization focused solely on maximizing…

Reinforcement Learning