cs.AI · cs.CL · cs.LG · cs.CV · cs.CR · cs.SE · stat.ML · q-fin.TR · q-fin.ST · econ.GN · q-bio.QM · physics.soc-ph · math.OC · cs.RO · cs.HC
Jad Yammine, Malek Wahidi, Abrar Anwar, Yan Chang, Mihir Acharya and others · 2026-10-20
Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs. For example, explaining recurring aisle blockages can require reviewing video from m…
Jingyu Xiao, Qianxi Liu, Yintong Huo, Yuan Jiang, Michael R. Lyu · 2026-10-20
Software engineering agents solve repository-level tasks through iterative tool use, but their continuously growing interaction traces incur substantial token consumption and inference overhead. Existing compression approaches often require model training, auxiliary LLM calls, or…
Jingyu Xiao, Dasen Dai, Yuxuan Wan, Jen-tse Huang, Yintong Huo and others · 2026-10-20
Interactive webpages underpin modern applications, but reproducing both their visual appearance and multi-step behavior remains challenging for multimodal large language models (MLLMs). Scalable training data must capture user actions, state transitions, and expected outcomes, wh…
Gaotang Li, Bhavana Dalvi Mishra, Yifei Ming, Yanfei Chen, Zhongying CuiZhu and others · 2026-10-20
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model. A single global harness can struggle with heterogeneous tasks that require different execution strategies. In this work, we introduce Object-Oriented Harness (OO-Harne…
Giuseppe Bisicchia, Alessandro Bocci, Jose Garcia-Alonso, Juan Manuel Murillo, Antonio Brogi · 2026-10-20
Cloud-accessible quantum computing has made heterogeneous Quantum Processing Units (QPUs) available through provider platforms that differ in qubit technology, calibration state, queueing behavior, and pricing model. This heterogeneity makes execution management a quantum-enginee…
Seyedeh Fatemeh Mirfakhar, Reda Snaiki, Rocio Lilen Segura · 2026-10-20
Post-event building assessment requires linking observed physical damage to its consequences for safety, habitability, functionality, and recovery. Yet post-disaster evidence is often heterogeneous, incomplete, and distributed across images and reconnaissance reports, while recov…
Akarsh Ashok, Dinil Mon Divakaran, Vivek Balachandran · 2026-10-20
ExeBench is one of the most widely used benchmarks for evaluating LLM-based decompilers. We analyze ExeBench and identify nine issues that affect how faithfully a test measures a decompiler. Three of them prevent LLM decompilers from recovering C code from ExeBench's function. Th…
Somin Kim, Robert Feldt, Shin Yoo · 2026-10-20
Testing LLM-based software is expensive: each input needs several sampled responses, each judged by a costly oracle. Further, every prompt or model change calls for re-testing. Pre-generation adequacy measures cut this cost by ranking inputs by failure risk based on the model's i…
Joschka Kersting, Gesa Benndorf · 2026-10-20
Programmable Logic Controller (PLC) coding remains a manual, IDE-centric task that demands constant context switching between documentation, project files, and code editors. Recent work has demonstrated that retrieval-augmented large language models can generate vendor-compliant …
Lili Quan, Longtian Wang, Yuelin Wang, Mingfei Cheng, Chao Shen and others · 2026-10-20
Large language model (LLM) agents increasingly execute business operations through tools and interact directly with application data and services. Beyond completing user requests, these agents must obey domain-specific business rules that constrain when actions are permitted and …
Lingxiao Tang, Wei Tao, Yiwen Guo, Lingfeng Bao · 2026-10-20
Training coding agents typically updates the policy while keeping the harness fixed. During training, trajectories reveal flawed repair strategies and interaction problems that vary across tasks and change as the policy learns. We introduce HarnessAdapt-RL, which trains the polic…
Taiheng Pan · 2026-10-20
Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a framework includes is one configuration change away for its users. We measure how often this happens. We trace seven open-source frameworks for RL post-training th…
Tong Zhang, Yuxuan Cheng, Ruimin Zhang, Yun Peng, Tao Xie · 2026-10-20
Applications provide convenient features for users to complete daily tasks. However, different users may have different or even conflicting requirements for the same application, while the requirements of the same user may change over time. Personalizing applications produced by …
Nada Zine, Matias Martinez, Romain Rouvoy, Clément Quinton · 2026-10-20
LLMs are increasingly integrated into software systems, making deployment and inference configuration a recurring software engineering task. Inference backends expose many options that affect model loading, generation, serving, and request processing. Yet little is known about wh…
Benjamin Donnot, Sami Tazi, Eva Boguslawski, Nourredine Henka · 2026-10-20
Learned surrogates for power-flow (PF) computation are usually motivated by speed, compared against a single CPU-based baseline. We show this comparison is fragile: across 7 open-source CPU-based solvers evaluated on identical inputs, throughput varies by roughly 2.5-3 orders of …
Siyuan Li, Jiayi Zhou, Zhiyuan Xia, Weijie Wang, Yaowen Zheng and others · 2026-10-20
Code reuse in modern software ecosystems facilitates the spread of 1-day vulnerabilities, posing significant security risks. Determining if patches are present is crucial, but traditional methods suffer from limited usability and accuracy, often depending on a fragile compilation…
Yali Du, Yunji Zhang, Ming Li · 2026-10-20
Code translation converts source code from one programming language to another while preserving its functionality. Although Large Language Models (LLMs) have improved code translation, their outputs still contain hallucinations: generated code that conflicts with the source progr…
Yue Xu, Xiyang Wang, Hui Liu, Bolei He · 2026-10-20
The increasing use of large language models for code generation calls for methods that distinguish purely human-written code from AI-involved code: files in which any part, however small, was generated or substantially modified by a model. Beyond flagging such files, we aim to lo…
Oleksiy V. Penkov, Boyang Shen · 2026-10-20
A published laboratory number can be verified only when its raw file and extraction method are known. This paper presents the value-level provenance architecture of APS ELN, an electronic laboratory notebook used by both researchers and language-model agents. The architecture was…
Riku Kato, Tatsuya Shirai, Olivier Nourry, Yutaro Kashiwa, Kenji Fujiwara and others · 2026-10-20
Continuous fuzzing is used for vulnerability detection in Open Source Software (OSS). Large-scale services such as Google's OSS-Fuzz fuzz over 1,300 projects and have revealed more than 10,000 vulnerabilities. Despite this, a considerable time lag often exists between when a vuln…
Wang Yi, Chengzi Huang, Behnam Khodabandeloo, Duc Anh Nguyen · 2026-10-20
Despite decades of progress in model-based methods and tools for embedded real-time systems, there is still no integrated environment that supports the entire development lifecycle. This paper presents MIMOS-Tools, a comprehensive toolchain spanning the key phases of development,…
Niclas Hart, Nicolas Weeger · 2026-10-20
Retrieval-Augmented Generation (RAG) has become the dominant paradigm for grounding the outputs of large language models (LLM) in external knowledge. However, practitioners are faced with a vast configuration space comprising chunking, embedding, retrieval, reranking, prompting a…
Olivier Nourry, Yoshiki Higo · 2026-10-20
Vulnerability benchmarks and software engineering research depend on rebuilding historical software. Yet builds rely on external resources, such as base images and packages, that change independently of the source code. In this study, we examine this environment decay on 14,159 O…
Wenjie Gan, Zhaoxi Zhang, Jiahui Liang, Weikang Li, Wanyuan Wang and others · 2026-10-20
Large Language Models have shown strong code generation capabilities, yet their outputs often contain subtle bugs. Automatically repairing such code requires informative tests: inputs that expose faulty behavior, paired with correct expected outputs. Recent RL-based test generati…
Martin Monperrus · 2026-10-20
For millennia, knowledge has been carried by language, and large language models still put language at the center. Yet the coding agents built on these models mostly write code. This paper is a contribution to epistemology, which asks what kind of knowledge code is and how it is …
Atanu Mukhopadhyay, Shravya Reddy Nalla · 2026-10-20
Rerunning every governance control after every change to an artificial intelligence (AI) pipeline is expensive, so teams reuse earlier results. Reuse is safe only if each control's declared dependencies cover everything that can change its outcome, and only if the release gate ch…
Tingxu Han, Wei Song, Ziming Li, Yuchen Chen, Weisong Sun and others · 2026-10-20
Automatically generating high-quality documentation for software repositories remains challenging: existing approaches largely treat documentation as unconstrained text generation, lacking explicit quality specifications, depending heavily on long-context prompts over raw code, a…
Zihan Chen, Di Zhu, Lei Nico Zheng · 2026-10-20
Recursive self-improvement (RSI) promises AI systems, such as self-evolving LLM agents, that become better at producing further improvements. Evaluating this promise requires separating product claims about the final system from process claims about the improvement process itself…
De Wang, Peng Qi · 2026-10-20
Agent platforms are starting to improve their own agents: they read a deployed agent's execution traces, derive a change, have an automated verifier approve it, and release it with no human author. How much of this loop can safely run without a human? We propose two quantities a …
Nishant Abhishek, Ping Charoenwet, Kla Tantithamthavorn · 2026-10-19
Finding vulnerabilities early, before they can affect the production system, is important for reducing the risk of any software attacks. However, detecting vulnerabilities during secure code review is still difficult because the vulnerable code logic may depend on lines found acr…
Will De Michele, Kla Tantithamthavorn · 2026-10-19
AI coding agents now contribute to software repositories at scale, yet their documentation practices remain uncharacterised. We analyse 29,669 AI-generated pull requests from 2,585 repositories in the AIDev dataset, measuring documentation co-change: whether code-file modificatio…
Matt Pope, Jonathan Sillito · 2026-10-19
BACKGROUND: After a software incident, organizations attempt to improve the reliability of their software systems by conducting post-incident analysis and identifying actions to prevent or mitigate similar future incidents. Despite the importance of this activity, there is a limi…
Daniel Keller, Rohit Kumar · 2026-10-19
Firmware diagnostic logging (printf) is an essential debug instrument in full-chip SoC design verification, yet it imposes a heavy tax on cycle-accurate RTL simulation: formatting a 30-character, 1-argument message on a simulated CPU and serializing it through an MMIO aperture co…
Qingxiao Xu, Ze Sheng, Zhicheng Chen, Arjun Manikandan, Jeff Huang · 2026-10-19
Rust is increasingly used in Linux to improve memory safety, but its guarantees do not prevent logical races: individually synchronized operations can still interleave in ways that violate higher-level invariants. Detecting such bugs typically requires manually written specificat…
Jyoti Prakash, Mikkel Baun Kjærgaard, Abhishek Tiwari · 2026-10-19
The WebView interface in Android (hybrid) applications enables the native side (e.g., Java) to exchange data with the Web (e.g., JavaScript). This creates cross-language information flow channels that existing single-language analyzers cannot analyze. Existing hybrid app analyses…
Andras L. Ferenczi, Mariya Bessonov, Allwyn Ponnudurai, Chandrakanth R. Mamillapalli, Krishna K. Maddula and others · 2026-10-19
Producing synthetic data for comparison testing a migrated COBOL application is a major challenge that agentic migrations face today. Our prior paper, the Agentic Method for Deterministic Validation of Legacy Code Migration, presents a deterministic oracle to facilitate such migr…
Ding Wang, Chao Jiang, Dugang Liu, Zhiwu Xu, Cheng Wen and others · 2026-10-19
Large language models (LLMs) are increasingly used to generate Verus contracts for Rust programs together with the proofs that establish them. Yet verifier acceptance, the common measure of success, shows only that the implementation satisfies the generated contract, so it leaves…
Amarsaikhan Batjargal, Noriko Tomuro · 2026-10-19
Reinforcement learning with verifiable rewards (RLVR) is particularly well suited to code generation because generated programs can be objectively evaluated through execution. Execution also provides behavioral information that can be reused as additional supervision. The Synergi…
Tianqi Liu, Yandong Guan, Songze Li, Wenkai Wang, Gang Yu and others · 2026-10-19
Coding agents increasingly undertake development tasks in mature enterprise repositories, yet existing benchmarks offer limited insight into whether they fulfill complete Product Requirement Documents (PRDs) and where delivery breaks down. Issue resolution and development from sc…
Dzikri Rahadian Fudholi, Andrea Capiluppi · 2026-10-19
Architectural roles describe how responsibilities are distributed within software systems. Entity--Boundary--Control (EBC) separates domain information, external interaction, and workflow coordination, but its proportions across diverse software remain unclear. This study examine…
GET https://store.agentexchange.work/gw/papers/latest?cat=cs.SE&limit=25 (0.003 USD per call). Catalogue