AI Software Engineering

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

33 new papers

A weekly snapshot of new work published in AI Software Engineering.

Period ending 2026-09-14

28 new papers

A weekly snapshot of new work published in AI Software Engineering.

Period ending 2026-09-07

37 new papers

A weekly snapshot of new work published in AI Software Engineering.

Inside this field

Focused directions

Focused topic

Code Generation

Within AI Software Engineering

324 papersExplore

Focused topic

Coding Agents

Within AI Software Engineering

278 papersExplore

Focused topic

Code Quality

Within AI Software Engineering

124 papersExplore

Focused topic

Software Engineering

Within AI Software Engineering

94 papersExplore

Focused topic

Test Generation

Within AI Software Engineering

70 papersExplore

Focused topic

Repository

Within AI Software Engineering

65 papersExplore

Focused topic

Software

Within AI Software Engineering

64 papersExplore

Focused topic

Swe-Bench Verified

Within AI Software Engineering

36 papersExplore

Focused topic

Codebases

Within AI Software Engineering

33 papersExplore

Focused topic

Commits

Within AI Software Engineering

32 papersExplore

Focused topic

Repository-Level Code Understanding

Within AI Software Engineering

31 papersExplore

946 papers

Latest in AI Software Engineering

Browse all topics →

Latent Anchor-Driven Test Generation for Deep Neural Networks
Jun 3, 2026Bin Duan, Matthew B. Dwyer, Guowei YangTest Generation Modern Deep Networks
The Impact of Configuring Agentic AI Coding Tools on Build-vs-Buy Decisions: A Study Protocol
Jun 2, 2026Jai Lal Lulla, Matthias Galster, Jie M. Zhang +2Coding Agents Tool
Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition
Jun 2, 2026Jinnuo Liu, Yue Peng, Jinhan Niu +1Code Generation Application Programming Interfaces
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
Jun 2, 2026Wenqi Chen, Ziyan Zhang, Bin Wang +3Large Language Model Safety Vulnerable Code
What Makes Interaction Trajectories Effective for Training Terminal Agents?
Jun 2, 2026Sidi Yang, Chaofan Tao, Jierun Chen +11Agentic Reinforcement-Learning Framework Pedagogy
SPOQ: Specialist Orchestrated Queuing for Multi-Agent Software Engineering
Jun 2, 2026Royce Carbowitz, Dheeraj KumarSoftware Engineering Multi-Agent Systems
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Jun 2, 2026Guhong Chen, Yingcheng Shi, Yongbin Li +6Agentic Reinforcement-Learning Framework Self-Evolving Agents
ModuLoop : Low-Level Code Generation using Modular Synthesizer and Closed-Loop Debugger for Robotic Control
Jun 2, 2026Gina Yoon, Sumin Lee, Joo Yong SimReal-World Manipulation Tasks Code Generation
Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks
Jun 1, 2026Dipesh KC, Anjila BudathokiCoding Agents Handoff
The Biomimetic Architecture of Software 4.0
Jun 1, 2026Philip Sheldrake, Dirk SchefflerSoftware Bio-Inspired Framework
FATE-VLA:Failue-aware test generation for vision-language-action models
Jun 1, 2026Arusa Kanwal, Pablo Valle, Shaukat Ali +1Vision-Language-Action Models Robot Policies
CodegenBench: Can LLMs Write Efficient Code Across Architectures?
Jun 1, 2026Jie Li, Wenzhao Wu, Junqi Hu +5High-Performance Computing Code Generation
EstRTL: Functional Estimation Guided RTL Code Generation
Jun 1, 2026Qi Xiong, Renzhi Chen, Bowei Wang +3Flexible Register Transfer Level Design Automation Register Transfer Level
MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics
Jun 1, 2026Žiga Kovačič, Kevin EllisPhysical Dynamics Code Generation
"Skill Issues'': Data-Centric Optimization of Lakehouse Agents
May 31, 2026Nicole Rose Schneider, Davide Ghilardi, Giacomo Piccinini +1Evaluation Harnesses Code Generation
ASE-26: a curriculum for agentic software engineering as a discipline
May 31, 2026Mikael GorskySoftware Engineering Coding Agents
Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Submissions
May 31, 2026Di WuArtificial Intelligence Reviewers Human-Agent Collaborative Paper-To-Page
FVSpec: Real-World Property-Based Tests as Lean Challenges
May 31, 2026Quinn Dougherty, Max von Hippel, Simon Henniger +2Formal Verification Test Generation
When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
May 31, 2026Xu Yang, Lunyiu Nie, Ethan Chandra +3Coding Agents Parallel
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
May 30, 2026Ming Wang, Shuang Wu, Bixuan Wang +7Psychometrics Psychology
Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
May 30, 2026Dongping Chen, Xuanao Huang, Zhihan Hu +3Multimodal Agents Omni-Modal
How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
May 29, 2026Nazmus AshrafiCode Generation Multi-Agent Large Language Model Systems
SEMBridge: Tagless-Final Program Semantics with Weakest-Precondition and Bounded-Checking Interpretations
May 29, 2026Eric LiangFormal Verification Mock-Interface Synthesis
Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection
May 29, 2026Maksuda Bilkis Baby, Khushika Shah, Naiyue Liang +1Data Leakage Code Quality
MIRAGE: Metadata-Integrated Repository Analysis and Guided Enhancement for MSR Datasets
May 29, 2026Aabia Ather, Muhammad Usayd Ather, Qurat-Ul-Ain Somroo +1Repository Citations
Knowledge Boundary Probing and Demand-Guided Intervention for LLM-Based Power System Code Generation
May 29, 2026Hui Wu, Xiaoyang Wang, Zhong FanCode Generation
Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages
May 29, 2026Fan Wu, Lishuai Dong, Cuiyun Gao +4Web Code Generation
Automatically Attacking Software Reverse Engineering AI Agents
May 28, 2026Brian Crawford, Justin Phillips, Patrick McClureReverse Engineering Disassembly
Improving Small Language Models for Code Generation with Reinforcement Learning from Verification Feedback
May 28, 2026Egor Skopin, Evgeny KotelnikovCode Generation Reinforcement Learning With Verifiable Reward
SpecBench: Evaluating Specification-Level Reasoning for Software Engineering LLM Agents
May 28, 2026Grant Hamblin, Kevin Song, Zhanda Zhu +4Software Engineering Swe-Bench Verified
Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency
May 28, 2026Chris Adams, Arjun Singh Banga, Parveen Bansal +28Code Quality Artificial Intelligence Reviewers
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
May 28, 2026Wanghan Xu, Shuo Li, Tianlin Ye +48Autoresearch Agentic Benchmarks
Projectional Decoding: Towards Semantic-Aware LLM Generation
May 28, 2026Boqi Chen, José Antonio Hernández López, Aren A. BabikianLarge Language Model Generation Code Generation
CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models
May 28, 2026Vedant PadwalBenchmarking Large Language Models Code Generation
Inferring Code Correctness from Specification
May 28, 2026Tambon Florian, Papadakis MikeCode Generation Correctness
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search
May 28, 2026Yunbo Tang, Chengyi Yang, Shiyu Liu +4Agentic Search Self-Awareness
Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
May 28, 2026Alexander Sternfeld, Andrei Kucharavy, Ljiljana DolamicVulnerable Code Vulnerability Detection & Repair
Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability
May 28, 2026Pedro Orvalho, Marta Kwiatkowska, Guillem Alenyà +1Large Language Model Reasoning Satisfiability
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
May 28, 2026Ningzhi Tang, Chaoran Chen, Gelei Xu +5Coding Agents Misalignment
Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
May 28, 2026Chia-Yi Hsu, Chia-Mu Yu, Chun-Ying Huang +1Indirect Prompt Injection Large Language Model Hallucination
Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA
May 28, 2026Jun Zhang, JianYing Qu, Hanwen Du +3Repository-Level Code Understanding Repository
The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems
May 27, 2026Nikolay Radev, Lennart Haas, Benjamin Arnav +1Sabotage Multi-Agent Systems
Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence
May 27, 2026Linxin Song, Jiefeng Chen, Yue Huang +5Codebases Equivalence
When Models Disagree: Rethinking LLM Evaluation for Public Comment Analysis
May 27, 2026Aisha Najera, Alvin Moon, Vedant Srinivasan +1Large Language Model Evaluation Inter-Rater Variability
Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests
May 27, 2026Richard J. Young, Gregory D. MoodyCode Quality Large Language Model Safety
LACUNA: Safe Agents as Recursive Program Holes
May 27, 2026Yaoyu Zhao, Yichen Xu, Oliver Bračevac +3Runtime Enforcement Code Generation
Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation
May 27, 2026Melih Catal, Alex Wolf, Tiago Ferreiro Matos +2Code Generation Implicit Bias
Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
May 27, 2026Andrea Gurioli, Davide D'Ascenzo, Federico Pennino +2Code Quality Code Generation
Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification
May 27, 2026Dylan Bouchard, Mohit Singh Chauhan, Zeya Ahmad +1Code Generation Natural Language Inference
Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning
May 27, 2026Mingze Wu, Abhinav Anand, Shweta Verma +1Code Generation LLM Post-Training Methods
From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence
May 27, 2026Raffael Theiler, Ludovico Comito, David Leko +3Reproducibility Mle-Bench Lite
ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
May 27, 2026Yihan Xia, Taotao WangAutoresearch Academic Papers
Commit to the Bit: Reactive Reinforcement Learning Done Right
May 27, 2026Onno Eberhard, Claire Vernade, Michael MuehlebachQ-Learning Markov Decision Processes
SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
May 27, 2026Yubin Qu, Yi Liu, Gelei Deng +4Coding Agents Benchmark Suite
Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generation
May 27, 2026Le Bronnec Florian, Alexandre Verine, Rio Yokota +1Code Generation Redundancy
STAB: Specification-driven Testing for Algorithmic Bottlenecks
May 27, 2026Soohan Lim, Joonghyuk Hahn, Hyundong Jin +1Test Generation Bottlenecks
FPMoE: A Sparse Mixture-of-Experts Approach to Functional Code Generation
May 27, 2026Loc Pham, Lang Hong Nguyet Anh, Thanh Le-CongMixture-Of-Expert Language Models Code Generation
Poison with Style: A Practical Poisoning Attack on Code Large Language Models
May 26, 2026Khang Tran, Yazan Boshmaf, Issa Khalil +3Language Model Evasion Attacks Data Poisoning
Agentic Separation Logic Specification Synthesis
May 26, 2026Tarun Suresh, David Korczynski, Julien VanegueMock-Interface Synthesis Cp-Agent
Libra: Training the Environment for Agentic Information Retrieval
May 26, 2026Xuan Zhao, Andy Chiu, Gengyu WangSwe-Bench Verified Environment

Jun 3, 2026 · cs.LGJ/K move · Enter open · S save

Latent Anchor-Driven Test Generation for Deep Neural Networks

Bin Duan, Matthew B. Dwyer, Guowei Yang

School of Electrical Engineering and Computer Science, The University of Queensland, Australia · Department of Computer Science, University of Virginia, United States

Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses. Existing DNN testing approaches explore either the input space or a learned latent space. While latent-space generation can better maintain plausibility than direct input-space mutation, current methods still face a trade-off among exploration controllability, failure diversity, and seed-relative semantic drift. To overcome these limitations, we propose Latte, a black-box testing framework that generates semantically proximate, diverse, and fault-revealing test cases by leveraging the latent space. Specifically, Latte encodes each input seed with a pre-trained VQ-VAE and performs a seed-centered, one-step latent mutation along directions defined by anchors sampled from alternative classes, followed by quantization and decoding back to the input space. This explores local neighborhoods around each seed within the learned latent manifold, resulting in a larger number and broader diversity of oracle-triggering prediction discrepancies under the same budget. We evaluated Latte on 5 datasets and 10 DNN models in single-model and multi-model testing scenarios. Across the evaluated datasets and models, Latte improves fault exposure and behavioral diversity under matched testing budgets. Under the single-model setting, it also maintains low seed-relative semantic drift with respect to the source seeds.

Test Generation Modern Deep Networks Latent Space Cryptographically Authorized Mutation Neural Network Taco

Open paper Ask about it PDF